We present DrivingGaussian++, an efficient and effective framework for realistic reconstruction and controllable editing of surrounding dynamic autonomous driving scenes. DrivingGaussian++ models the static background with incremental 3D Gaussians and reconstructs moving objects with a composite dynamic Gaussian graph, ensuring accurate positions and occlusions. By integrating a LiDAR prior, it achieves detailed and consistent scene reconstruction, outperforming existing methods in dynamic scene reconstruction and photorealistic surround-view synthesis. DrivingGaussian++ supports training-free controllable editing for dynamic driving scenes, including texture modification, weather simulation, and object manipulation, leveraging multi-view images and depth priors. By integrating large language models (LLMs) and controllable editing, our method can automatically generate dynamic object motion trajectories and enhance their realism during the optimization process. DrivingGaussian++ demonstrates consistent and realistic editing results and generates dynamic multi-view driving scenarios, while significantly enhancing scene diversity.

Despite the recent progress, existing frame interpolation methods still struggle with processing extremely high resolution input and handling challenging cases such as repetitive textures, thin objects, and large motion. To address these issues, we introduce a patch-based cascaded pixel diffusion model for high resolution frame interpolation, HiFI, that excels in these scenarios while achieving competitive performance on standard benchmarks. Cascades, which generate a series of images from low to high resolution, can help significantly with large or complex motion that require both global context for a coarse solution and detailed context for high resolution output. However, contrary to prior work on cascaded diffusion models which perform diffusion on increasingly large resolutions, we use a single model that always performs diffusion at the same resolution and upsamples by processing patches of the inputs and the prior solution. At inference time, this drastically reduces memory usage and allows a single model, solving both frame interpolation (base model’s task) and spatial up-sampling, saving training cost as well. HiFI excels at high-resolution images and complex repeated textures that require global context, achieving comparable or state-of-the-art performance on various benchmarks (Vimeo, Xiph, X-Test, and SEPE-8K). We further introduce a new dataset, LaMoR, that focuses on particularly challenging cases, and HiFI significantly outperforms other baselines.

Motion control is crucial for generating expressive and compelling video content; however, most existing video generation models rely mainly on text prompts for control, which struggle to capture the nuances of dynamic actions and temporal compositions. To this end, we train a video generation model conditioned on spatiotemporally sparse or dense motion trajectories. In contrast to prior motion conditioning work, this flexible representation can encode any number of trajectories, object-specific or global scene motion, and temporally sparse motion; due to its flexibility we refer to this conditioning as motion prompts. While users may directly specify sparse trajectories, we also show how to translate high-level user requests into detailed, semi-dense motion prompts, a process we term motion prompt expansion. We demonstrate the versatility of our approach through various applications, including camera and object motion control, "interacting" with an image, motion transfer, and image editing. Our results showcase emergent behaviors, such as realistic physics, suggesting the potential of motion prompts for probing video models and interacting with future generative world models. Finally, we evaluate quantitatively, conduct a human study, and demonstrate strong performance.

Estimating geometry from dynamic scenes, where objects move and deform over time, remains a core challenge in computer vision. Current approaches often rely on multi-stage pipelines or global optimizations that decompose the problem into subtasks, like depth and flow, leading to complex systems prone to errors. In this paper, we present Motion DUSt3R (MonST3R), a novel geometry-first approach that directly estimates per-timestep geometry from dynamic scenes. Our key insight is that by simply estimating a pointmap for each timestep, we can effectively adapt DUSt3R’s representation, previously only used for static scenes, to dynamic scenes. However, this approach presents a significant challenge: the scarcity of suitable training data, namely dynamic, posed videos with depth labels. Despite this, we show that by posing the problem as a fine-tuning task, identifying several suitable datasets, and strategically training the model on this limited data, we can surprisingly enable the model to handle dynamics, even without an explicit motion representation. Based on this, we introduce new optimizations for several downstream video-specific tasks and demonstrate strong performance on video depth and camera pose estimation, outperforming prior work in terms of robustness and efficiency. Moreover, MonST3R shows promising results for primarily feed-forward 4D reconstruction. Interactive 4D results, source code, and trained models are available at: https://monst3r-project.github.io/.

Scaling up autoregressive models in vision has not proven as beneficial as in large language models. In this work, we investigate this scaling problem in the context of text-to-image generation, focusing on two critical factors: whether models use discrete or continuous tokens, and whether tokens are generated in a random or fixed raster order using BERT- or GPT-like transformer architectures. Our empirical results show that, while all models scale effectively in terms of validation loss, their evaluation performance -- measured by FID, GenEval score, and visual quality -- follows different trends. Models based on continuous tokens achieves significantly better visual quality than those using discrete tokens. Furthermore, the generation order and attention mechanisms significantly affect the GenEval score: random-order models achieve notably better GenEval scores compared to raster-order models. Inspired by these findings, we train Fluid, a random-order autoregressive model on continuous tokens. Fluid 10.5B model achieves a new state-of-the-art zeor-shot FID of 6.16 on MS-COCO 30K, and 0.69 overall score on the GenEval benchmark. We hope our findings and results will encourage future efforts to further bridge the scaling gap between vision and language models.

Recent progress in image generation has sparked research into controlling these models through condition signals, with various methods addressing specific challenges in conditional generation. Instead of proposing another specialized technique, we introduce a simple, unified framework to handle diverse conditional generation tasks involving a specific image-condition correlation. By learning a joint distribution over a correlated image pair (e.g. image and depth) with a diffusion model, our approach enables versatile capabilities via different inference-time sampling schemes, including controllable image generation (e.g. depth to image), estimation (e.g. image to depth), signal guidance, joint generation (image \& depth), and coarse control. Previous attempts at unification often introduce complexity through multi-stage training, architectural modification, or increased parameter counts. In contrast, our simplified formulation requires a single, computationally efficient training stage, maintains the standard model input, and adds minimal learned parameters (15% of the base model). Moreover, our model supports additional capabilities like non-spatially aligned and coarse conditioning. Extensive results show that our single model can produce comparable results with specialized methods and better results than prior unified methods. We also demonstrate that multiple models can be effectively combined for multi-signal conditional generation.

Recent advances in video generation models have sparked interest in world models capable of simulating realistic environments. While navigation has been well-explored, physically meaningful interactions that mimic real-world forces remain largely understudied. In this work, we investigate using physical forces as a control signal for video generation and propose force prompts which enable users to interact with images through both localized point forces, such as poking a plant, and global wind force fields, such as wind blowing on fabric. We demonstrate that these force prompts can enable videos to respond realistically to physical control signals by leveraging the physical prior in the original pretrained model, without using any 3D asset or physics simulator at inference. The primary challenge of force prompting is the difficulty in obtaining high quality paired force-video training data, both in the real world due to the difficulty of obtaining force signals, and in synthetic data due to limitations in the visual quality and domain diversity of physics simulators. Our key finding is that video generation models can *generalize* remarkably well when adapted to follow physical force conditioning from videos synthesized by Blender, even with limited demonstrations of few objects (e.g., flying flags, rolling balls, etc.). Our method can generate videos which simulate forces across diverse geometries, settings, and materials. We also try to understand the source of this generalization and perform ablations on the training data that reveal two key elements: visual diversity and the use of specific text keywords during training. Our approach is trained on only around 15k training examples for a single day on four A100 GPUs, and outperforms existing methods on force adherence and physics realism, bringing world models closer to real-world physics interactions. All datasets, code, and model weights will be open-sourced. Video examples can be found at https://sites.google.com/view/force-prompting-neurips2025

Current 3D scene understanding methods are limited by offline-collected multi-view data or pre-constructed 3D geometry. In this paper, we present ExtractAnything3D (EA3D), a unified online framework for open-world 3D object extraction that enables simultaneous geometric reconstruction and holistic scene understanding. Given a streaming video, EA3D dynamically interprets each frame using vision-language and 2D vision foundation encoders to extract object-level knowledge. This knowledge is integrated and embedded into a Gaussian feature map via a feed-forward online update strategy. We then iteratively estimate visual odometry from historical frames and incrementally update online Gaussian features with new observations. A recurrent joint optimization module directs the model's attention to regions of interest, simultaneously enhancing both geometric reconstruction and semantic understanding. Extensive experiments across diverse benchmarks and tasks, including photo-realistic rendering, semantic and instance segmentation, 3D bounding box and semantic occupancy estimation, and 3D mesh generation, demonstrate the effectiveness of EA3D. Our method establishes a unified and efficient framework for joint online 3D reconstruction and holistic scene understanding, enabling a broad range of downstream tasks. The project webpage is available at \url{https://github.com/VDIGPKU/EA3D}.

While text-to-video generation shows state-of-the-art results, fine-grained output control remains challenging for users relying solely on natural language prompts. In this work, we present FACTOR for fine-grained controllable video generation. FACTOR provides an intuitive interface where users can manipulate the trajectory and appearance of individual objects in conjunction with a text prompt. We propose a unified framework to integrate these control signals into an existing text-to-video model. Our approach involves a multimodal condition module with a joint encoder, control-attention layers, and an appearance augmentation mechanism. This design enables FACTOR to generate videos that closely align with detailed user specifications. Extensive experiments on standard benchmarks and user-provided inputs demonstrate a notable improvement in controllability by FACTOR over competitive baselines.

We propose a new dataset and a novel approach to learning hand-object interaction priors for hand and articulated object pose estimation. We first collect a dataset using visual teleoperation, where the human operator can directly play within a physical simulator to manipulate the articulated objects. We record the data and obtain free and accurate annotations on object poses and contact information from the simulator. Our system only requires an iPhone to record human hand motion, which can be easily scaled up and largely lower the costs of data and annotation collection. With this data, we learn 3D interaction priors including a discriminator (in a GAN) capturing the distribution of how object parts are arranged, and a diffusion model which generates the contact regions on articulated objects, guiding the hand pose estimation. Such structural and contact priors can easily transfer to real-world data with barely any domain gap. By using our data and learned priors, our method significantly improves the performance on joint hand and articulated object poses estimation over the existing state-of-the-art methods. The project is available at https://zehaozhu.github.io/ContactArt/.

While pre-trained large-scale vision models have shown significant promise for semantic correspondence, their features often struggle to grasp the geometry and orientation of instances. This paper identifies the importance of being geometry-aware for semantic correspondence and reveals a limitation of the features of current foundation models under simple post-processing. We show that incorporating this information can markedly enhance semantic correspondence performance with simple but effective solutions in both zero-shot and supervised settings. We also construct a new challenging benchmark for semantic correspondence built from an existing animal pose estimation dataset, for both pre-training validating models. Our method achieves a [email protected] score of 65.4 (zero-shot) and 85.6 (supervised) on the challenging SPair-71k dataset, surpassing the state of the art by 5.5p and 11.0p absolute gains, respectively. Our code and datasets are publicly available at: https://telling-left-from-right.github.io.

We introduce One-shot Open Affordance Learning (OOAL), where a model is trained with just one example per base object category, but is expected to identify novel objects and affordances. While vision-language models excel at recognizing novel objects and scenes, they often struggle to understand finer levels of granularity such as affordances. To handle this issue, we conduct a comprehensive analysis of existing foundation models, to explore their inherent understanding of affordances and assess the potential for data-limited affordance learning. We then propose a vision-language framework with simple and effective designs that boost the alignment between visual features and affordance text embeddings. Experiments on two affordance segmentation benchmarks show that the proposed method outperforms state-of-the-art models with less than 1% of the full training data, and exhibits reasonable generalization capability on unseen objects and affordances. Project page: https://reagan1311.github.io/ooal.

Recent advances in large-scale pretraining have yielded visual foundation models with strong capabilities. Not only can recent models generalize to arbitrary images for their training task, their intermediate representations are useful for other visual tasks such as detection and segmentation. Given that such models can classify, delineate, and local- ize objects in 2D, we ask whether they also represent their 3D structure? In this work, we analyze the 3D awareness of visual foundation models. We posit that 3D awareness implies that representations (1) encode the 3D structure of the scene and (2) consistently represent the surface across views. We conduct a series of experiments using task-specific probes and zero-shot inference procedures on frozen fea- tures. Our experiments reveal several limitations of the current models. Our code and analysis can be found at https://github.com/mbanani/probe3d.

We present SHINOBI, an end-to-end frameworkfor the re-construction of shape, material, and illumination from object images captured with varying lighting, pose, and background. Inverse rendering of an object based on unconstrained image collections is a long-standing challenge in computer vision and graphics and requires a joint optimization over shape, radiance, and pose. We show that an implicit shape repre-sentation based on a multi-resolution hash encoding enables faster and robust shape reconstruction with joint camera alignment optimization that outperforms prior work. Further, to enable the editing of illumination and object reflectance (i.e. material) we jointly optimize BRDF and illumination to-gether with the object's shape. Our method is class-agnostic and works on in-the-wild image collections of objects to produce relightable 3D assets for several use cases such as AR/VR, movies, games, etc.

We introduce a 3D-aware diffusion model, ZeroNVS, for single-image novel view synthesis for in-the-wild scenes. While existing methods are designed for single objects with masked backgrounds, we propose new techniques to address challenges introduced by in-the-wild multi-object scenes with complex backgrounds. Specifically, we train a generative prior on a mixture of data sources that capture object-centric, indoor, and outdoor scenes. To address issues from data mixture such as depth-scale ambiguity, we propose a novel camera conditioning parameterization and normalization scheme. Further, we observe that Score Distillation Sampling (SDS) tends to truncate the distribution of complex backgrounds during distillation of 360-degree scenes, and propose “SDS anchoring” to improve the diversity of synthesized novel views. Our model sets a new state-of-the-art result in LPIPS on the DTU dataset in the zero-shot setting, even outperforming methods specifically trained on DTU. We further adapt the challenging Mip-NeRF 360 dataset as a new benchmark for single-image novel view synthesis, and demonstrate strong performance in this setting. Code and models are available at this url.

We introduce WonderJourney, a modular framework for perpetual 3D scene generation. Unlike prior work on view generation that focuses on a single type of scenes, we start at any user-provided location (by a text description or an image), and generate a journey through a long sequence of diverse yet coherently connected 3D scenes. We leverage an LLM to generate textual descriptions of the scenes in this journey, a text-driven point cloud generation pipeline to make a compelling and coherent sequence of 3D scenes, and a large VLM to verify the generated scenes. We show compelling, diverse visual results across various scene types and styles, forming imaginary “wonder journeys ”. Project website: https://kovenyu.com/WonderJourney/. “No, no! The adventures first, explanations take such a dreadful time.“ - Alice's Adventures in Wonderland

We present DrivingGaussian, an efficient and effective framework for surrounding dynamic autonomous driving scenes. For complex scenes with moving objects, we first sequentially and progressively model the static background of the entire scene with incremental static 3D Gaussians. We then leverage a composite dynamic Gaussian graph to handle multiple moving objects, individually reconstructing each object and restoring their accurate positions and occlusion relationships within the scene. We further use a LiDAR prior for Gaussian Splatting to reconstruct scenes with greater details and maintain panoramic consistency. DrivingGaussian outperforms existing methods in dynamic driving scene reconstruction and enables photorealistic surround-view synthesis with high-fidelity and multi-camera consistency. Our project page is at: https:/github.com/VDIGPKU/DrivingGaussian.

We present a novel approach named OmniControl for incorporating flexible spatial control signals into a text-conditioned human motion generation model based on the diffusion process. Unlike previous methods that can only control the pelvis trajectory, OmniControl can incorporate flexible spatial control signals over different joints at different times with only one model. Specifically, we propose analytic spatial guidance that ensures the generated motion can tightly conform to the input control signals. At the same time, realism guidance is introduced to refine all the joints to generate more coherent motion. Both the spatial and realism guidance are essential and they are highly complementary for balancing control accuracy and motion realism. By combining them, OmniControl generates motions that are realistic, coherent, and consistent with the spatial constraints. Experiments on HumanML3D and KIT-ML datasets show that OmniControl not only achieves significant improvement over state-of-the-art methods on pelvis control but also shows promising results when incorporating the constraints over other joints. Project page: https://neu-vi.github.io/omnicontrol/.

We present GALA3D, generative 3D GAussians with LAyout-guided control, for effective compositional text-to-3D generation. We first utilize large language models (LLMs) to generate the initial layout and introduce a layout-guided 3D Gaussian representation for 3D content generation with adaptive geometric constraints. We then propose an instance-scene compositional optimization mechanism with conditioned diffusion to collaboratively generate realistic 3D scenes with consistent geometry, texture, scale, and accurate interactions among multiple objects while simultaneously adjusting the coarse layout priors extracted from the LLMs to align with the generated scene. Experiments show that GALA3D is a user-friendly, end-to-end framework for state-of-the-art scene-level 3D content generation and controllable editing while ensuring the high fidelity of object-level entities within the scene. The source codes and models will be available at gala3d.github.io.

Humans excel at acquiring knowledge through observation. For example, we can learn to use new tools by watching demonstrations. This skill is fundamental for intelligent systems to interact with the world. A key step to acquire this skill is to identify what part of the object affords each action, which is called affordance grounding. In this paper, we address this problem and propose a framework called LOCATE that can identify matching object parts across images, to transfer knowledge from images where an object is being used (exocentric images used for learning), to images where the object is inactive (egocentric ones used to test). To this end, we first find interaction areas and extract their feature embeddings. Then we learn to aggregate the embeddings into compact prototypes (human, object part, and background), and select the one representing the object part. Finally, we use the selected prototype to guide affordance grounding. We do this in a weakly supervised manner, learning only from image-level affordance and object labels. Extensive experiments demonstrate that our approach outperforms state-of-the-art methods by a large margin on both seen and unseen objects.11Project page: https://reagan1311.github.io/locate.

Recently, AutoFlow has shown promising results on learning a training set for optical flow, but requires ground truth labels in the target domain to compute its search metric. Observing a strong correlation between the ground truth search metric and self-supervised losses, we introduce self-supervised AutoFlow to handle real-world videos without ground truth labels. Using self-supervised loss as the search metric, our self-supervised AutoFlow performs on par with AutoFlow on Sintel and KITTI where ground truth is available, and performs better on the real-world DAVIS dataset. We further explore using self-supervised AutoFlow in the (semi-)supervised setting and obtain competitive results against the state of the art.

Recovering lighting in a scene from a single image is a fundamental problem in computer vision. While a mirror ball light probe can capture omnidirectional lighting, light probes are generally unavailable in everyday images. In this work, we study recovering lighting from accidental light probes (ALPs)-common, shiny objects like Coke cans, which often accidentally appear in daily scenes. We propose a physically-based approach to model ALPs and estimate lighting from their appearances in single images. The main idea is to model the appearance of ALPs by photogram-metrically principled shading and to invert this process via differentiable rendering to recover incidental illumination. We demonstrate that we can put an ALP into a scene to allow high-fidelity lighting estimation. Our model can also recover lighting for existing images that happen to contain an ALP**Project website: https://kovenyu.com/ALP. I'd rather be Shiny. - Tamatoa from Moana, 2016

Recent work has shown the possibility of training generative models of 3D content from 2D image collections on small datasets corresponding to a single object class, such as human faces, animal faces, or cars. However, these models struggle on larger, more complex datasets. To model diverse and unconstrained image collections such as ImageNet, we present VQ3D, which introduces a NeRF-based decoder into a two-stage vector-quantized autoencoder. Our Stage 1 allows for the reconstruction of an input image and the ability to change the camera position around the image, and our Stage 2 allows for the generation of new 3D scenes. VQ3D is capable of generating and reconstructing 3D-aware images from the 1000-class ImageNet dataset of 1.2 million training images, and achieves a competitive ImageNet generation FID score of 16.8. Our project webpage is at this url.

Recent novel view synthesis methods obtain promising results for relatively small scenes, e.g., indoor environments and scenes with a few objects, but tend to fail for unbounded outdoor scenes with a single image as input. In this paper, we introduce SAMPLING, a Scene-adaptive Hierarchical Multiplane Images Representation for Novel View Synthesis from a Single Image based on improved multiplane images (MPI). Observing that depth distribution varies significantly for unbounded outdoor scenes, we employ an adaptive-bins strategy for MPI to arrange planes in accordance with each scene image. To represent intricate geometry and multi-scale details, we further introduce a hierarchical refinement branch, which results in high-quality synthesized novel views. Our method demonstrates considerable performance gains in synthesizing large-scale unbounded outdoor scenes using a single image on the KITTI dataset and generalizes well to the unseen Tanks and Temples dataset. The code and models will be made available at https://pkuvdig.github.io/SAMPLING/.

Denoising diffusion probabilistic models have transformed image generation with their impressive fidelity and diversity. We show that they also excel in estimating optical flow and monocular depth, surprisingly without task-specific architectures and loss functions that are predominant for these tasks. Compared to the point estimates of conventional regression-based methods, diffusion models also enable Monte Carlo inference, e.g., capturing uncertainty and ambiguity in flow and depth. With self-supervised pre-training, the combined use of synthetic and real data for supervised training, and technical innovations (infilling and step-unrolled denoising diffusion training) to handle noisy-incomplete training data, one can train state-of-the-art diffusion models for depth and optical flow estimation, with additional zero-shot coarse-to-fine refinement for high resolution estimates. Extensive experiments focus on quantitative performance against benchmarks, ablations, and the model's ability to capture uncertainty and multimodality, and impute missing values. Our model obtains a state-of-the-art relative depth error of 0.074 on the indoor NYU benchmark and an Fl-all score of 3.26\% on the KITTI optical flow benchmark, about 25\% better than the best published method.

Text-to-image diffusion models have made significant advances in generating and editing high-quality images. As a result, numerous approaches have explored the ability of diffusion model features to understand and process single images for downstream tasks, e.g., classification, semantic segmentation, and stylization. However, significantly less is known about what these features reveal across multiple, different images and objects. In this work, we exploit Stable Diffusion (SD) features for semantic and dense correspondence and discover that with simple post-processing, SD features can perform quantitatively similar to SOTA representations. Interestingly, the qualitative analysis reveals that SD features have very different properties compared to existing representation learning features, such as the recently released DINOv2: while DINOv2 provides sparse but accurate matches, SD features provide high-quality spatial information but sometimes inaccurate semantic matches. We demonstrate that a simple fusion of these two features works surprisingly well, and a zero-shot evaluation using nearest neighbors on these fused features provides a significant performance gain over state-of-the-art methods on benchmark datasets, e.g., SPair-71k, PF-Pascal, and TSS. We also show that these correspondences can enable interesting applications such as instance swapping in two images. Project page: https://sd-complements-dino.github.io/.

DSLR cameras can achieve multiple zoom levels via shifting lens distances or swapping lens types. However, these techniques are not possible on smart-phone devices due to space constraints. Most smartphone manufacturers adopt a hybrid zoom system: commonly a Wide ( W ) camera at a low zoom level and a Telephoto ( T ) camera at a high zoom level. To simulate zoom levels between W and T , these systems crop and digitally upsample images from W , leading to significant detail loss. In this paper, we propose an efficient system for hybrid zoom super-resolution on mobile devices, which captures a synchronous pair of W and T shots and leverages machine learning models to align and transfer details from T to W. We further develop an adaptive blending method that accounts for depth-of-field mismatches, scene occlusion, flow uncertainty, and alignment errors. To minimize the domain gap, we design a dual-phone camera rig to capture real-world inputs and ground-truths for supervised training. Our method generates a 12-megapixel image in 500ms on a mobile platform and compares favorably against state-of-the-art methods under extensive evaluation on real-world scenarios.

Data is the driving force of machine learning, with the amount and quality of training data often being more important for the performance of a system than architecture and training details. But collecting, processing and annotating real data at scale is difficult, expensive, and frequently raises additional privacy, fairness and legal concerns. Synthetic data is a powerful tool with the potential to address these shortcomings: 1) it is cheap 2) supports rich ground-truth annotations 3) offers full control over data and 4) can circumvent or mitigate problems regarding bias, privacy and licensing. Unfortunately, software tools for effective data generation are less mature than those for architecture design and training, which leads to fragmented generation efforts. To address these problems we introduce Kubric, an open-source Python framework that interfaces with PyBullet and Blender to generate photo-realistic scenes, with rich annotations, and seamlessly scales to large jobs distributed over thousands of machines, and generating TBs of data. We demonstrate the effectiveness of Kubric by presenting a series of 13 different generated datasets for tasks ranging from studying 3D NeRF models to optical flow estimation. We release Kubric, the used assets, all of the generation code, as well as the rendered datasets for reuse and modification.

Aggressive data augmentation is a key component of the strong generalization capabilities of Vision Transformer (ViT). One such data augmentation technique is adversarial training (AT); however, many prior works [28,45] have shown that this often results in poor clean accuracy. In this work, we present pyramid adversarial training (PyramidAT), a simple and effective technique to improve ViT's overall performance. We pair it with a “matched” Dropout and stochastic depth regularization, which adopts the same Dropout and stochastic depth configuration for the clean and adversarial samples. Similar to the improvements on CNNs by AdvProp [61] (not directly applicable to ViT), our pyramid adversarial training breaks the trade-off between in-distribution accuracy and out-of-distribution robustness for ViT and related architectures. It leads to 1.82% absolute improvement on ImageNet clean accuracy for the ViT-B model when trained only on ImageNet-1K data, while simultaneously boosting performance on 7 ImageNet ro-bustness metrics, by absolute numbers ranging from 1.76% to 15.68%. We set a new state-of-the-art for ImageNet-C (41.42 mCE), ImageNet-R (53.92%), and ImageNet-Sketch (41.04%) without extra data, using only the ViT-B/16 backbone and our pyramid adversarial training. Our code is publicly available at pyramidat.github.io.

Predicting multiple future frames from a given video is a challenging problem due to several factors such as changing camera, dynamically moving objects, occlusions, etc. While recent deep learning methods have made significant progress on the video prediction problem, most methods predict the immediate or a fixed number of future frames. To obtain longer-term frame predictions, existing techniques usually process the predicted frames iteratively, resulting in blurry or inconsistent predictions. In this work, we present a new approach that can predict an arbitrary number of future video frames with a single forward pass through the network. Instead of directly predicting a fixed number of future optical flows or frames, we learn temporal motion encodings, i.e., temporal motion basis vectors and a network to predict the coefficients. The learned motion basis can be easily extended to arbitrary length at inference time, enabling us to predict an arbitrary number of future frames. Experiments on benchmark datasets show that our approach performs favorably against several competitive techniques even for the next frame prediction setting. When evaluated under 5-frame or 10-frame prediction settings, the proposed method achieves higher performance gains over the state-of-the-art techniques that iteratively process the predictions.

Inverse rendering of an object under entirely unknown capture conditions is a fundamental challenge in computer vision and graphics. Neural approaches such as NeRF have achieved photorealistic results on novel view synthesis, but they require known camera poses. Solving this problem with unknown camera poses is highly challenging as it requires joint optimization over shape, radiance, and pose. This problem is exacerbated when the input images are captured in the wild with varying backgrounds and illuminations. Standard pose estimation techniques fail in such image collections in the wild due to very few estimated correspondences across images. Furthermore, NeRF cannot relight a scene under any illumination, as it operates on radiance (the product of reflectance and illumination). We propose a joint optimization framework to estimate the shape, BRDF, and per-image camera pose and illumination. Our method works on in-the-wild online image collections of an object and produces relightable 3D assets for several use-cases such as AR/VR. To our knowledge, our method is the first to tackle this severely unconstrained task with minimal user interaction.

Motion blur of fast-moving subjects is a longstanding problem in photography and very common on mobile phones due to limited light collection efficiency, particularly in low-light conditions. While we have witnessed great progress in image deblurring in recent years, most methods require significant computational power and have limitations in processing high-resolution photos with severe local motions. To this end, we develop a novel face deblurring system based on the dual camera fusion technique for mobile phones. The system detects subject motion to dynamically enable a reference camera, e.g., ultrawide angle camera commonly available on recent premium phones, and captures an auxiliary photo with faster shutter settings. While the main shot is low noise but blurry (Figure 1(a)), the reference shot is sharp but noisy (Figure 1(b)). We learn ML models to align and fuse these two shots and output a clear photo without motion blur (Figure 1(c)). Our algorithm runs efficiently on Google Pixel 6, which takes 463 ms overhead per shot. Our experiments demonstrate the advantage and robustness of our system against alternative single-image, multi-frame, face-specific, and video deblurring algorithms as well as commercial products. To the best of our knowledge, our work is the first mobile solution for face motion deblurring that works reliably and robustly over thousands of images in diverse motion and lighting conditions.

Prototype learning is extensively used for few-shot segmentation. Typically, a single prototype is obtained from the support feature by averaging the global object information. However, using one prototype to represent all the information may lead to ambiguities. In this paper, we propose two novel modules, named superpixel-guided clustering (SGC) and guided prototype allocation (GPA), for multiple prototype extraction and allocation. Specifically, SGC is a parameter-free and training-free approach, which extracts more representative prototypes by aggregating similar feature vectors, while GPA is able to select matched prototypes to provide more accurate guidance. By integrating the SGC and GPA together, we propose the Adaptive Superpixel-guided Network (ASGNet), which is a lightweight model and adapts to object scale and shape variation. In addition, our network can easily generalize to k-shot segmentation with substantial improvement and no additional computational cost. In particular, our evaluations on COCO demonstrate that ASGNet surpasses the state-of-the-art method by 5% in 5-shot segmentation.1

Synthetic datasets play a critical role in pre-training CNN models for optical flow, but they are painstaking to generate and hard to adapt to new applications. To automate the process, we present AutoFlow, a simple and effective method to render training data for optical flow that optimizes the performance of a model on a target dataset. AutoFlow takes a layered approach to render synthetic data, where the motion, shape, and appearance of each layer are controlled by learnable hyperparameters. Experimental results show that AutoFlow achieves state-of-the-art accuracy in pre-training both PWC-Net and RAFT. Our code and data are available at autoflow-google.github.io.

In this paper, we address the problem of building dense correspondences between human images under arbitrary camera viewpoints and body poses. Prior art either assumes small motion between frames or relies on local descriptors, which cannot handle large motion or visually ambiguous body parts, e.g., left vs. right hand. In contrast, we propose a deep learning framework that maps each pixel to a feature space, where the feature distances reflect the geodesic distances among pixels as if they were projected onto the surface of a 3D human scan. To this end, we introduce novel loss functions to push features apart according to their geodesic distances on the surface. Without any semantic annotation, the proposed embeddings automatically learn to differentiate visually similar parts and align different subjects into an unified feature space. Extensive experiments show that the learned embeddings can produce accurate correspondences between images with remarkable generalization capabilities on both intra and inter subjects.1

Remarkable progress has been made in 3D reconstruction of rigid structures from a video or a collection of images. However, it is still challenging to reconstruct nonrigid structures from RGB inputs, due to its under-constrained nature. While template-based approaches, such as parametric shape models, have achieved great success in modeling the "closed world" of known object categories, they cannot well handle the "open-world" of novel object categories or outlier shapes. In this work, we introduce a template-free approach to learn 3D shapes from a single video. It adopts an analysis-by-synthesis strategy that forward-renders object silhouette, optical flow, and pixel values to compare with video observations, which generates gradients to adjust the camera, shape and motion parameters. Without using a category-specific shape template, our method faithfully reconstructs nonrigid 3D structures from videos of human, animals, and objects of unknown classes. Our code is available at lasr-google.github.io.

We introduce ViSER, a method for recovering articulated 3D shapes and dense3D trajectories from monocular videos. Previous work on high-quality reconstruction of dynamic 3D shapes typically relies on multiple camera views, strong category-specific priors, or 2D keypoint supervision. We show that none of these are required if one can reliably estimate long-range correspondences in a video, making use of only 2D object masks and two-frame optical flow as inputs. ViSER infers correspondences by matching 2D pixels to a canonical, deformable 3D mesh via video-specific surface embeddings that capture the pixel appearance of each surface point. These embeddings behave as a continuous set of keypoint descriptors defined over the mesh surface, which can be used to establish dense long-range correspondences across pixels. The surface embeddings are implemented as coordinate-based MLPs that are fit to each video via self-supervised losses.Experimental results show that ViSER compares favorably against prior work on challenging videos of humans with loose clothing and unusual poses as well as animals videos from DAVIS and YTVOS. Project page: viser-shape.github.io.

We present a simple and effective image super-resolution algorithm that imposes an image formation constraint on the deep neural networks via pixel substitution. The proposed algorithm first uses a deep neural network to estimate intermediate high-resolution images, blurs the intermediate images using known blur kernels, and then substitutes values of the pixels at the un-decimated positions with those of the corresponding pixels from the low-resolution images. The output of the pixel substitution process strictly satisfies the image formation model and is further refined by the same deep neural network in a cascaded manner. The proposed framework is trained in an end-to-end fashion and can work with existing feed-forward deep neural networks for super-resolution and converges fast in practice. Extensive experimental results show that the proposed algorithm performs favorably against state-of-the-art methods.

We investigate two crucial and closely-related aspects of CNNs for optical flow estimation: models and training. First, we design a compact but effective CNN model, called PWC-Net, according to simple and well-established principles: pyramidal processing, warping, and cost volume processing. PWC-Net is 17 times smaller in size, 2 times faster in inference, and 11 percent more accurate on Sintel final than the recent FlowNet2 model. It is the winning entry in the optical flow competition of the robust vision challenge. Next, we experimentally analyze the sources of our performance gains. In particular, we use the same training procedure for PWC-Net to retrain FlowNetC, a sub-network of FlowNet2. The retrained FlowNetC is 56 percent more accurate on Sintel final than the previously trained one and even 5 percent more accurate than the FlowNet2 model. We further improve the training procedure and increase the accuracy of PWC-Net on Sintel by 10 percent and on KITTI 2012 and 2015 by 20 percent. Our newly trained model parameters and training protocols are available on https://github.com/NVlabs/PWC-Net.

We address the unsupervised learning of several interconnected problems in low-level vision: single view depth prediction, camera motion estimation, optical flow, and segmentation of a video into the static scene and moving regions. Our key insight is that these four fundamental vision problems are coupled through geometric constraints. Consequently, learning to solve them together simplifies the problem because the solutions can reinforce each other. We go beyond previous work by exploiting geometry more explicitly and segmenting the scene into static and moving regions. To that end, we introduce Competitive Collaboration, a framework that facilitates the coordinated training of multiple specialized neural networks to solve complex problems. Competitive Collaboration works much like expectation-maximization, but with neural networks that act as both competitors to explain pixels that correspond to static or moving regions, and as collaborators through a moderator that assigns pixels to be either static or independently moving. Our novel method integrates all these problems in a common framework and simultaneously reasons about the segmentation of the scene into moving objects and the static background, the camera motion, depth of the static scene structure, and the optical flow of moving objects. Our model is trained without any supervision and achieves state-of-the-art performance among joint unsupervised methods on all sub-problems.

Convolutions are the fundamental building blocks of CNNs. The fact that their weights are spatially shared is one of the main reasons for their widespread use, but it is also a major limitation, as it makes convolutions content-agnostic. We propose a pixel-adaptive convolution (PAC) operation, a simple yet effective modification of standard convolutions, in which the filter weights are multiplied with a spatially varying kernel that depends on learnable, local pixel features. PAC is a generalization of several popular filtering techniques and thus can be used for a wide range of use cases. Specifically, we demonstrate state-of-the-art performance when PAC is used for deep joint image upsampling. PAC also offers an effective alternative to fully-connected CRF (Full-CRF), called PAC-CRF, which performs competitively compared to Full-CRF, while being considerably faster. In addition, we also demonstrate that PAC can be used as a drop-in replacement for convolution layers in pre-trained networks, resulting in consistent performance improvements.

We introduce a compact network for holistic scene flow estimation, called SENSE, which shares common encoder features among four closely-related tasks: optical flow estimation, disparity estimation from stereo, occlusion estimation, and semantic segmentation. Our key insight is that sharing features makes the network more compact, induces better feature representations, and can better exploit interactions among these tasks to handle partially labeled data. With a shared encoder, we can flexibly add decoders for different tasks during training. This modular design leads to a compact and efficient model at inference time. Exploiting the interactions among these tasks allows us to introduce distillation and self-supervised losses in addition to supervised losses, which can better handle partially labeled real-world data. SENSE achieves state-of-the-art results on several optical flow benchmarks and runs as fast as networks specifically designed for optical flow. It also compares favorably against the state of the art on stereo and scene flow, while consuming much less memory.

Learning to synthesize high frame rate videos via interpolation requires large quantities of high frame rate training videos, which, however, are scarce, especially at high resolutions. Here, we propose unsupervised techniques to synthesize high frame rate videos directly from low frame rate videos using cycle consistency. For a triplet of consecutive frames, we optimize models to minimize the discrepancy between the center frame and its cycle reconstruction, obtained by interpolating back from interpolated intermediate frames. This simple unsupervised constraint alone achieves results comparable with supervision using the ground truth intermediate frames. We further introduce a pseudo supervised loss term that enforces the interpolated frames to be consistent with predictions of a pre-trained interpolation model. The pseudo supervised loss term, used together with cycle consistency, can effectively adapt a pre-trained model to a new target domain. With no additional data and in a completely unsupervised fashion, our techniques significantly improve pre-trained models on new target domains, increasing PSNR values from 32.84dB to 33.05dB on the Slowflow and from 31.82dB to 32.53dB on the Sintel evaluation datasets.

To date, top-performing optical flow estimation methods only take pairs of consecutive frames into account. While elegant and appealing, the idea of using more than two frames has not yet produced state-of-the-art results. We present a simple, yet effective fusion approach for multi-frame optical flow that benefits from longer-term temporal cues. Our method first warps the optical flow from previous frames to the current, thereby yielding multiple plausible estimates. It then fuses the complementary information carried by these estimates into a new optical flow field. At the time of writing, our method ranks first among published results in the MPI Sintel and KITTI 2015 benchmarks. Our models will be available on https://github.com/NVlabs/PWC-Net.

We study domain-specific video streaming. Specifically, we target a streaming setting where the videos to be streamed from a server to a client are all in the same domain and they have to be compressed to a small size for low-latency transmission. Several popular video streaming services, such as the video game streaming services of GeForce Now and Twitch, fall in this category. While conventional video compression standards such as H.264 are commonly used for this task, we hypothesize that one can leverage the property that the videos are all in the same domain to achieve better video quality. Based on this hypothesis, we propose a novel video compression pipeline. Specifically, we first apply H.264 to compress domain-specific videos. We then train a novel binary autoencoder to encode the leftover domain-specific residual information frame-by-frame into binary representations. These binary representations are then compressed and sent to the client together with the H.264 stream. In our experiments, we show that our pipeline yields consistent gains over standard H.264 compression across several benchmark datasets while using the same channel bandwidth.

Given two consecutive frames, video interpolation aims at generating intermediate frame(s) to form both spatially and temporally coherent video sequences. While most existing methods focus on single-frame interpolation, we propose an end-to-end convolutional neural network for variable-length multi-frame video interpolation, where the motion interpretation and occlusion reasoning are jointly modeled. We start by computing bi-directional optical flow between the input images using a U-Net architecture. These flows are then linearly combined at each time step to approximate the intermediate bi-directional optical flows. These approximate flows, however, only work well in locally smooth regions and produce artifacts around motion boundaries. To address this shortcoming, we employ another U-Net to refine the approximated flow and also predict soft visibility maps. Finally, the two input images are warped and linearly fused to form each intermediate frame. By applying the visibility maps to the warped images before fusion, we exclude the contribution of occluded pixels to the interpolated intermediate frame to avoid artifacts. Since none of our learned network parameters are time-dependent, our approach is able to produce as many intermediate frames as needed. To train our network, we use 1,132 240-fps video clips, containing 300K individual video frames. Experimental results on several datasets, predicting different numbers of interpolated frames, demonstrate that our approach performs consistently better than existing methods.

In this paper, we propose a general dual convolutional neural network (DualCNN) for low-level vision problems, e.g., super-resolution, edge-preserving filtering, deraining and dehazing. These problems usually involve the estimation of two components of the target signals: structures and details. Motivated by this, our proposed DualCNN consists of two parallel branches, which respectively recovers the structures and details in an end-to-end manner. The recovered structures and details can generate the target signals according to the formation model for each particular application. The DualCNN is a flexible framework for low-level vision tasks and can be easily incorporated into existing CNNs. Experimental results show that the DualCNN can be effectively applied to numerous low-level vision tasks with favorable performance against the state-of-the-art methods.

We present a network architecture for processing point clouds that directly operates on a collection of points represented as a sparse set of samples in a high-dimensional lattice. Naively applying convolutions on this lattice scales poorly, both in terms of memory and computational cost, as the size of the lattice increases. Instead, our network uses sparse bilateral convolutional layers as building blocks. These layers maintain efficiency by using indexing structures to apply convolutions only on occupied parts of the lattice, and allow flexible specifications of the lattice structure enabling hierarchical and spatially-aware feature learning, as well as joint 2D-3D reasoning. Both point-based and image-based representations can be easily incorporated in a network with such layers and the resulting model can be trained in an end-to-end manner. We present results on 3D segmentation tasks where our approach outperforms existing state-of-the-art techniques.

We present a compact but effective CNN model for optical flow, called PWC-Net. PWC-Net has been designed according to simple and well-established principles: pyramidal processing, warping, and the use of a cost volume. Cast in a learnable feature pyramid, PWC-Net uses the current optical flow estimate to warp the CNN features of the second image. It then uses the warped features and features of the first image to construct a cost volume, which is processed by a CNN to estimate the optical flow. PWC-Net is 17 times smaller in size and easier to train than the recent FlowNet2 model. Moreover, it outperforms all published optical flow methods on the MPI Sintel final pass and KITTI 2015 benchmarks, running at about 35 fps on Sintel resolution (1024 Ã × 436) images. Our models are available on our project website.

Superpixel segmentation has been widely used in many computer vision tasks. Existing superpixel algorithms are mainly based on hand-crafted features, which often fail to preserve weak object boundaries. In this work, we leverage deep neural networks to facilitate extracting superpixels from images. We show a simple integration of deep features with existing superpixel algorithms does not result in better performance as these features do not model segmentation. Instead, we propose a segmentation-aware affinity learning approach for superpixel segmentation. Specifically, we propose a new loss function that takes the segmentation error into account for affinity learning. We also develop the Pixel Affinity Net for affinity prediction. Extensive experimental results show that the proposed algorithm based on the learned segmentation-aware loss performs favorably against the state-of-the-art methods. We also demonstrate the use of the learned superpixels in numerous vision applications with consistent improvements.

We present an effective blind image deblurring algorithm based on the dark channel prior. The motivation of this work is an interesting observation that the dark channel of blurred images is less sparse. While most patches in a clean image contain some dark pixels, this is not the case when they are averaged with neighboring ones by motion blur. This change in sparsity of the dark channel pixels is an inherent property of the motion blur process, which we prove mathematically and validate using image data. Enforcing sparsity of the dark channel thus helps blind deblurring in various scenarios such as natural, face, text, and low-illumination images. However, imposing sparsity of the dark channel introduces a non-convex non-linear optimization problem. In this work, we introduce a linear approximation to address this issue. Extensive experiments demonstrate that the proposed deblurring algorithm achieves the state-of-the-art results on natural images and performs favorably against methods designed for specific scenarios. In addition, we show that the proposed method can be applied to image dehazing.

Given two consecutive frames from a pair of stereo cameras, 3D scene flow methods simultaneously estimate the 3D geometry and motion of the observed scene. Many existing approaches use superpixels for regularization, but may predict inconsistent shapes and motions inside rigidly moving objects. We instead assume that scenes consist of foreground objects rigidly moving in front of a static background, and use semantic cues to produce pixel-accurate scene flow estimates. Our cascaded classification framework accurately models 3D scenes by iteratively refining semantic segmentation masks, stereo correspondences, 3D rigid motion estimates, and optical flow fields. We evaluate our method on the challenging KITTI autonomous driving benchmark, and show that accounting for the motion of segmented vehicles leads to state-of-the-art performance.

We present an algorithm to directly restore a clear highresolution image from a blurry low-resolution input. This problem is highly ill-posed and the basic assumptions for existing super-resolution methods (requiring clear input) and deblurring methods (requiring high-resolution input) no longer hold. We focus on face and text images and adopt a generative adversarial network (GAN) to learn a category-specific prior to solve this problem. However, the basic GAN formulation does not generate realistic high-resolution images. In this work, we introduce novel training losses that help recover fine details. We also present a multi-class GAN that can process multi-class image restoration tasks, i.e., face and text images, using a single generator network. Extensive experiments demonstrate that our method performs favorably against the state-of-the-art methods on both synthetic and real-world images at a lower computational cost.

Visual formats have advanced beyond single-view images and videos: 3D movies are commonplace, researchers have developed multi-view navigation systems, and VR is helping to push light field cameras to mass market. However, editing tools for these media are still nascent, and even simple filtering operations like color correction or stylization are problematic: naively applying image filters per frame or per view rarely produces satisfying results due to time and space inconsistencies. Our method preserves and stabilizes filter effects while being agnostic to the inner working of the filter. It captures filter effects in the gradient domain, then uses input frame gradients as a reference to impose temporal and spatial consistency. Our least-squares formulation adds minimal overhead compared to naive data processing. Further, when filter cost is high, we introduce a filter transfer strategy that reduces the number of per-frame filtering computations by an order of magnitude, with only a small reduction in visual quality. We demonstrate our algorithm on several camera array formats including stereo videos, light fields, and wide baselines.

We present a simple and effective blind image deblurring method based on the dark channel prior. Our work is inspired by the interesting observation that the dark channel of blurred images is less sparse. While most image patches in the clean image contain some dark pixels, these pixels are not dark when averaged with neighboring highintensity pixels during the blur process. This change in the sparsity of the dark channel is an inherent property of the blur process, which we both prove mathematically and validate using training data. Therefore, enforcing the sparsity of the dark channel helps blind deblurring on various scenarios, including natural, face, text, and low-illumination images. However, sparsity of the dark channel introduces a non-convex non-linear optimization problem. We introduce a linear approximation of the min operator to compute the dark channel. Our look-up-table-based method converges fast in practice and can be directly extended to non-uniform deblurring. Extensive experiments show that our method achieves state-of-the-art results on deblurring natural images and compares favorably methods that are well-engineered for specific scenarios.

Existing optical flow methods make generic, spatially homogeneous, assumptions about the spatial structure of the flow. In reality, optical flow varies across an image depending on object class. Simply put, different objects move differently. Here we exploit recent advances in static semantic scene segmentation to segment the image into objects of different types. We define different models of image motion in these regions depending on the type of object. For example, we model the motion on roads with homographies, vegetation with spatially smooth flow, and independently moving objects like cars and planes with affine motion plus deviations. We then pose the flow estimation problem using a novel formulation of localized layers, which addresses limitations of traditional layered models for dealing with complex scene motion. Our semantic flow method achieves the lowest error of any published monocular method in the KITTI-2015 flow benchmark and produces qualitatively better flow and segmentation than recent top methods on a wide range of natural videos.

As consumer depth sensors become widely available, estimating scene flow from RGBD sequences has received increasing attention. Although the depth information allows the recovery of 3D motion from a single view, it poses new challenges. In particular, depth boundaries are not well-aligned with RGB image edges and therefore not reliable cues to localize 2D motion boundaries. In addition, methods that extend the 2D optical flow formulation to 3D still produce large errors in occlusion regions. To better use depth for occlusion reasoning, we propose a layered RGBD scene flow method that jointly solves for the scene segmentation and the motion. Our key observation is that the noisy depth is sufficient to decide the depth ordering of layers, thereby avoiding a computational bottleneck for RGB layered methods. Furthermore, the depth enables us to estimate a per-layer 3D rigid motion to constrain the motion of each layer. Experimental results on both the Middlebury and real-world sequences demonstrate the effectiveness of the layered approach for RGBD scene flow estimation.

Extending image processing techniques to videos is a non-trivial task; applying processing independently to each video frame often leads to temporal inconsistencies, and explicitly encoding temporal consistency requires algorithmic changes. We describe a more general approach to temporal consistency. We propose a gradient-domain technique that is blind to the particular image processing algorithm. Our technique takes a series of processed frames that suffers from flickering and generates a temporally-consistent video sequence. The core of our solution is to infer the temporal regularity from the original unprocessed video, and use it as a temporal consistency guide to stabilize the processed sequence. We formally characterize the frequency properties of our technique, and demonstrate, in practice, its ability to stabilize a wide range of popular image processing techniques including enhancement and stylization of color and tone, intrinsic images, and depth estimation.

Most motion estimation algorithms (optical flow, layered models) cannot handle large amount of occlusion in textureless regions, as motion is often initialized with no occlusion assumption despite that occlusion may be included in the final objective. To handle such situations, we propose a local layering model where motion and occlusion relationships are inferred jointly. In particular, the uncertainties of occlusion relationships are retained so that motion is inferred by considering all the possibilities of local occlusion relationships. In addition, the local layering model handles articulated objects with self-occlusion. We demonstrate that the local layering model can handle motion and occlusion well for both challenging synthetic and real sequences.

The accuracy of optical flow estimation algorithms has been improving steadily as evidenced by results on the Middlebury optical flow benchmark. The typical formulation, however, has changed little since the work of Horn and Schunck. We attempt to uncover what has made recent advances possible through a thorough analysis of how the objective function, the optimization method, and modern implementation practices influence accuracy. We discover that “classical” flow formulations perform surprisingly well when combined with modern optimization and implementation techniques. One key implementation detail is the median filtering of intermediate flow fields during optimization. While this improves the robustness of classical methods it actually leads to higher energy solutions, meaning that these methods are not optimizing the original objective function. To understand the principles behind this phenomenon, we derive a new objective function that formalizes the median filtering heuristic. This objective function includes a non-local smoothness term that robustly integrates flow estimates over large spatial neighborhoods. By modifying this new term to include information about flow and image boundaries we develop a method that can better preserve motion details. To take advantage of the trend towards video in wide-screen format, we further introduce an asymmetric pyramid downsampling scheme that enables the estimation of longer range horizontal motions. The methods are evaluated on the Middlebury, MPI Sintel, and KITTI datasets using the same parameter settings.

Although multiframe super resolution has been extensively studied in past decades, super resolving real-world video sequences still remains challenging. In existing systems, either the motion models are oversimplified or important factors such as blur kernel and noise level are assumed to be known. Such models cannot capture the intrinsic characteristics that may differ from one sequence to another. In this paper, we propose a Bayesian approach to adaptive video super resolution via simultaneously estimating underlying motion, blur kernel, and noise level while reconstructing the original high-resolution frames. As a result, our system not only produces very promising super resolution results outperforming the state of the art, but also adapts to a variety of noise levels and blur kernels. To further analyze the effect of noise and blur kernel, we perform a two-step analysis using the Cramer-Rao bounds. We study how blur kernel and noise influence motion estimation with aliasing signals, how noise affects super resolution with perfect motion, and finally how blur kernel and noise influence super resolution with unknown motion. Our analysis results confirm empirical observations, in particular that an intermediate size blur kernel achieves the optimal image reconstruction results.

Layered models allow scene segmentation and motion estimation to be formulated together and to inform one another. Traditional layered motion methods, however, employ fairly weak models of scene structure, relying on locally connected Ising/Potts models which have limited ability to capture long-range correlations in natural scenes. To address this, we formulate a fully-connected layered model that enables global reasoning about the complicated segmentations of real objects. Optimization with fully-connected graphical models is challenging, and our inference algorithm leverages recent work on efficient mean field updates for fully-connected conditional random fields. These methods can be implemented efficiently using high-dimensional Gaussian filtering. We combine these ideas with a layered flow model, and find that the long-range connections greatly improve segmentation into figure-ground layers when compared with locally connected MRF models. Experiments on several benchmark datasets show that the method can recover fine structures and large occlusion regions, with good flow accuracy and much lower computational cost than previous locally-connected layered models.

Layered models provide a compelling approach for estimating image motion and segmenting moving scenes. Previous methods, however, have failed to capture the structure of complex scenes, provide precise object boundaries, effectively estimate the number of layers in a scene, or robustly determine the depth order of the layers. Furthermore, previous methods have focused on optical flow between pairs of frames rather than longer sequences. We show that image sequences with more frames are needed to resolve ambiguities in depth ordering at occlusion boundaries; temporal layer constancy makes this feasible. Our generative model of image sequences is rich but difficult to optimize with traditional gradient descent methods. We propose a novel discrete approximation of the continuous objective in terms of a sequence of depth-ordered MRFs and extend graph-cut optimization methods with new “moves” that make joint layer segmentation and motion estimation feasible. Our optimizer, which mixes discrete and continuous optimization, automatically determines the number of layers and reasons about their depth ordering. We demonstrate the value of layered models, our optimization strategy, and the use of more than two frames on both the Middlebury optical flow benchmark and the MIT layer segmentation benchmark.

Although multi-frame super resolution has been extensively studied in past decades, super resolving real-world video sequences still remains challenging. In existing systems, either the motion models are oversimplified, or important factors such as blur kernel and noise level are assumed to be known. Such models cannot deal with the scene and imaging conditions that vary from one sequence to another. In this paper, we propose a Bayesian approach to adaptive video super resolution via simultaneously estimating underlying motion, blur kernel and noise level while reconstructing the original high-res frames. As a result, our system not only produces very promising super resolution results that outperform the state of the art, but also adapts to a variety of noise levels and blur kernels. Theoretical analysis of the relationship between blur kernel, noise level and frequency-wise reconstruction rate is also provided, consistent with our experimental results.

The accuracy of optical flow estimation algorithms has been improving steadily as evidenced by results on the Middlebury optical flow benchmark. The typical formulation, however, has changed little since the work of Horn and Schunck. We attempt to uncover what has made recent advances possible through a thorough analysis of how the objective function, the optimization method, and modern implementation practices influence accuracy. We discover that “classical” flow formulations perform surprisingly well when combined with modern optimization and implementation techniques. Moreover, we find that while median filtering of intermediate flow fields during optimization is a key to recent performance gains, it leads to higher energy solutions. To understand the principles behind this phenomenon, we derive a new objective that formalizes the median filtering heuristic. This objective includes a nonlocal term that robustly integrates flow estimates over large spatial neighborhoods. By modifying this new term to include information about flow and image boundaries we develop a method that ranks at the top of the Middlebury benchmark.

Layered models are a powerful way of describing natural scenes containing smooth surfaces that may overlap and occlude each other. For image motion estimation, such models have a long history but have not achieved the wide use or accuracy of non-layered methods. We present a new probabilistic model of optical flow in layers that addresses many of the shortcomings of previous approaches. In particular, we define a probabilistic graphical model that explicitly captures: 1) occlusions and disocclusions; 2) depth ordering of the layers; 3) temporal consistency of the layer segmentation. Additionally the optical flow in each layer is modeled by a combination of a parametric model and a smooth deviation based on an MRF with a robust spatial prior; the resulting model allows roughness in layers. Finally, a key contribution is the formulation of the layers using an image-dependent hidden field prior based on recent models for static scene segmentation. The method achieves state-of-the-art results on the Middlebury benchmark and produces meaningful scene segmentations as well as detected occlusion regions.

Transform coding using the discrete cosine transform (DCT) has been widely used in image and video coding standards, but at low bit rates, the coded images suffer from severe visual distortions which prevent further bit reduction. Postprocessing can reduce these distortions and alleviate the conflict between bit rate reduction and quality preservation. Viewing postprocessing as an inverse problem, we solve it via a Bayesian approach. The distortion caused by coding is modeled as additive, spatially correlated Gaussian noise, while the original image is modeled as a high order Markov random field (MRF) based on the recently proposed fields of experts (FoE) framework. Experimental results show that the proposed method, in most cases, achieves higher PSNR gain than other methods and the processed images possess good visual quality.

Transform coding using the discrete cosine transform (DCT) has been widely used in image and video coding standards, but at low bit rates, the coded images suffer from severe visual distortions which prevent further bit reduction. Postprocessing can reduce these distortions and alleviate the conflict between bit rate reduction and quality preservation. Viewing postprocessing as an inverse problem, we propose to solve it by the maximum a posteriori criterion. The distortion caused by coding is modeled as additive, spatially correlated Gaussian noise, while the original image is modeled as a high order Markov random field based on the fields of experts framework. Experimental results show that the proposed method, in most cases, achieves higher PSNR gain than other methods and the processed images possess good visual quality. In addition, we examine the noise model used and its parameter setting. The noise model assumes that the DCT coefficients and their quantization errors are independent. This assumption is no longer valid when the coefficients are truncated. We explain how this problem can be rectified using the current parameter setting.