An ideal traffic simulator replicates the realistic long-term point-to-point trip that a self-driving system experiences during deployment. Prior models and benchmarks focus on closed-loop motion simulation for initial agents in a scene. This is problematic for long-term simulation. Agents enter and exit the scene as the ego vehicle enters new regions. We propose InfGen, a unified next-token prediction model that performs interleaved closed-loop motion simulation and scene generation. InfGen automatically switches between closed-loop motion simulation and scene generation mode. It enables stable long-term rollout simulation. InfGen performs at the state-of-the-art in short-term (9s) traffic simulation, and significantly outperforms all other methods in long-term (30s) simulation. The code and model of InfGen will be released at https://orangesodahub.github.io/InfGen

We propose a new transformer-based image and video tokenizer with Binary Spherical Quantization (BSQ). BSQ projects the high-dimensional visual embedding to a lower-dimensional hypersphere and then applies binary quantization. BSQ is (1) parameter-efficient without an explicit codebook, (2) scalable to arbitrary token dimensions, and (3) compact: compressing visual data by up to 100× with minimal distortion. Our tokenizer uses a transformer encoder and decoder with simple block-wise causal masking to support variable-length videos as input. The resulting BSQ-ViT achieves state-of-the-art visual reconstruction quality on image and video reconstruction benchmarks with 2.4× throughput compared to the best prior methods. Furthermore, by learning an autoregressive prior for adaptive arithmetic coding, BSQ-ViT achieves comparable visual compression results with commonly used compression standards, e.g. JPEG2000/WebP for images and H.264/H.265 for videos. BSQ-ViT also enables masked language models to achieve competitive image synthesis quality to GAN and diffusion approaches.

Multi-modal large language models (MLLMs) have shown incredible capabilities in a variety of 2D vision and language tasks. We extend MLLMs’ perceptual capabilities to ground and reason about images in 3-dimensional space. To that end, we first develop a large-scale pretraining dataset for 2D and 3D called LV3D by combining multiple existing 2D and 3D recognition datasets under a common task formulation: as multi-turn question-answering. Next, we introduce a new MLLM named CUBE-LLM and pre-train it on LV3D. We show that pure data scaling makes a strong 3D perception capability without 3D specific architectural design or training objective. CUBE-LLM exhibits intriguing properties similar to LLMs: (1) CUBE-LLM can apply chain-of-thought prompting to improve 3D understanding from 2D context information. (2) CUBE-LLM can follow complex and diverse instructions and adapt to versatile input and output formats. (3) CUBE-LLM can be visually prompted such as 2D box or a set of candidate 3D boxes from specialists. Our experiments on outdoor benchmarks demonstrate that CUBE-LLM significantly outperforms existing baselines by 21.3 points of AP-BEV on the Talk2Car dataset for 3D grounded reasoning and 17.7 points on the DriveLM dataset for complex reasoning about driving scenarios, respectively. CUBE-LLM also shows competitive results in general MLLM benchmarks such as refCOCO for 2D grounding with (87.0) average score, as well as visual question answering benchmarks such as VQAv2, GQA, SQA, POPE, etc. for complex reasoning.

Protein language (or sequence) models, like the popular ESM2, are now widely used tools for extracting evolution-based protein representations and have achieved significant success on core downstream biological tasks. A major open problem is how to obtain representations that best capture both the sequence evolutionary history and the atomic structural properties of proteins in general. We introduce **I**mplicit **S**equence **M**odel, a sequence-only input model with structurally-enriched representations that outperforms state-of-the-art sequence models on several well-studied benchmarks including mutation stability assessment and structure prediction. Our key innovations are a microenvironment-based Autoencoder for generating structure tokens and a self-supervised training objective that distills these tokens into ESM2's pre-trained model. Notably, we make ISM's structure-enriched weights easily accessible for any application using the ESM2 framework.

Not yet. We present SPACE, a benchmark that systematically evaluates spatial cognition in frontier models. Our benchmark builds on decades of research in cognitive science. It evaluates large-scale mapping abilities that are brought to bear when an organism traverses physical environments, smaller-scale reasoning about object shapes and layouts, and cognitive infrastructure such as spatial attention and memory. For many tasks, we instantiate parallel presentations via text and images, allowing us to benchmark both large language models and large multimodal models. Results suggest that contemporary frontier models fall short of the spatial intelligence of animals, performing near chance level on a number of classic tests of animal cognition.

As language models grow ever larger, so do their vocabularies. This has shifted the memory footprint of LLMs during training disproportionately to one single layer: the cross-entropy in the loss computation. Cross-entropy builds up a logit matrix with entries for each pair of input tokens and vocabulary items and, for small models, consumes an order of magnitude more memory than the rest of the LLM combined. We propose Cut Cross-Entropy (CCE), a method that computes the cross-entropy loss without materializing the logits for all tokens into global memory. Rather, CCE only computes the logit for the correct token and evaluates the log-sum-exp over all logits on the fly. We implement a custom kernel that performs the matrix multiplications and the log-sum-exp reduction over the vocabulary in flash memory, making global memory consumption for the cross-entropy computation negligible. This has a dramatic effect. Taking the Gemma 2 (2B) model as an example, CCE reduces the memory footprint of the loss computation from 24 GB to 1 MB, and the total training-time memory consumption of the classifier head from 28 GB to 1 GB. To improve the throughput of CCE, we leverage the inherent sparsity of softmax and propose to skip elements of the gradient computation that have a negligible (i.e. below numerical precision) contribution to the gradient. Experiments demonstrate that the dramatic reduction in memory consumption is accomplished without sacrificing training speed or convergence.

Self-play has powered breakthroughs in two-player and multi-player games. Here we show that self-play is a surprisingly effective strategy in another domain. We show that robust and naturalistic driving emerges entirely from self-play in simulation at unprecedented scale -- 1.6 billion km of driving. This is enabled by Gigaflow, a batched simulator that can synthesize and train on 42 years of subjective driving experience per hour on a single 8-GPU node. The resulting policy achieves state-of-the-art performance on three independent autonomous driving benchmarks. The policy outperforms the prior state of the art when tested on recorded real-world scenarios, amidst human drivers, without ever seeing human data during training. The policy is realistic when assessed against human references and achieves unprecedented robustness, averaging 17.5 years of continuous driving between incidents in simulation.

Vision-language models are integral to computer vision research, yet many high-performing models remain closed-source, obscuring their data, design and training recipe. The research community has responded by using distillation from black-box models to label training data, achieving strong benchmark results, at the cost of measurable scientific progress. However, without knowing the details of the teacher model and its data sources, scientific progress remains difficult to measure. In this paper, we study building a Perception Language Model (PLM) in a fully open and reproducible framework for transparent research in image and video understanding. We analyze standard training pipelines without distillation from proprietary models and explore large-scale synthetic data to identify critical data gaps, particularly in detailed video understanding. To bridge these gaps, we release 2.8M human-labeled instances of fine-grained video question-answer pairs and spatio-temporally grounded video captions. Additionally, we introduce PLM–VideoBench, a suite for evaluating challenging video understanding tasks focusing on the ability to reason about ''what'', ''where'', ''when'', and ''how'' of a video. We make our work fully reproducible by providing data, training recipes, code & models.

The recent advance in vision-language models is largely attributed to the abundance of image-text data. We aim to replicate this success for video-language models, but there simply is not enough human-curated video-text data available. We thus resort to fine-tuning a video-language model from a strong image-language baseline with syn-thesized instructional data. The resulting video model by video-instruction-tuning (VIIT) is then used to auto-label millions of videos to generate high-quality captions. We show the adapted video-language model performs well on a wide range of video-language benchmarks. For instance, it surpasses the best prior result on open-ended NExT-QA by 2.8%. Besides, our model generates detailed descriptions for previously unseen videos, which provide better textual supervision than existing methods. Experiments show that a video-language dual-encoder model contrastively trained on these auto-generated captions is 3.8% better than the strongest baseline that also leverages vision-language models. Our best model outperforms state-of-the-art methods on MSR-VTT zero-shot text-to-video retrieval by 6%. As a side product, we generate the largest video capation dataset to date.

We present a new open-vocabulary detection framework. Our framework uses both image-level labels and detailed detection annotations when available. Our framework proceeds in three steps. We first train a language-conditioned object detector on fully-supervised detection data. This detector gets to see the presence or absence of ground truth classes during training, and conditions prediction on the set of present classes. We use this detector to pseudo-label images with image-level labels. Our detector provides much more accurate pseudo-labels than prior approaches with its conditioning mechanism. Finally, we train an unconditioned open-vocabulary detector on the pseudo-annotated images. The resulting detector, named DECOLA, shows strong zero-shot performance in open-vocabulary LVIS benchmark as well as direct zero-shot transfer benchmarks on LVIS, COCO, Object365, and Open/m-ages. DECOLA outperforms the prior arts by 17.1 APrareand 9.4 mAP on zero-shot LVIS benchmark. DECOLA achieves state-of-the-art results in various model sizes, architectures, and datasets by only training on open-sourced data and academic-scale computing. Code is available at https://github.com/janghyuncho/DECOLA.

We introduce LAVILA, a new approach to learning video-language representations by leveraging Large Language Models (LLMs). We repurpose pre-trained LLMs to be conditioned on visual input, and finetune them to create automatic video narrators. Our auto-generated narrations offer a number of advantages, including dense coverage of long videos, better temporal synchronization of the visual information and text, and much higher diversity of text. The video-language embedding learned contrastively with these narrations outperforms the previous state-of-the-art on multiple first-person and third-person video tasks, both in zero-shot and finetuned setups. Most notably, Lavilaobtains an absolute gain of 10.1% on EGTEA classification and 5.9% Epic-Kitchens-100 multi-instance retrieval benchmarks. Furthermore, LaVilatrained with only half the narrations from the Ego4D dataset outperforms models trained on the full set, and shows positive scaling behavior on increasing pre-training data and model size.

We present a scalable framework to learn part segmentation from object instance labels. State-of-the-art instance segmentation models contain a surprising amount of part information. However, much of this information is hidden from plain view. For each object instance, the part information is noisy, inconsistent, and incomplete. PartDistillation transfers the part information of an instance segmentation model into a part segmentation model through self-supervised self-training on a large dataset. The resulting segmentation model is robust, accurate, and generalizes well. We evaluate the model on various part segmentation datasets. Our model outperforms supervised part segmentation in zero-shot generalization performance by a large margin. Our model outperforms when finetuned on target datasets compared to supervised counterpart and other baselines especially in few-shot regime. Finally, our model provides a wider coverage of rare parts when evaluated over 10K object classes. Code is at https://github.com/facebookresearch/PartDistillation.

Stabilizing proteins is a foundational step in protein engineering. However, the evolutionary pressure of all extant proteins makes identifying the scarce number of mutations that will improve thermodynamic stability challenging. Deep learning has recently emerged as a powerful tool for identifying promising mutations. Existing approaches, however, are computationally expensive, as the number of model inferences scales with the number of mutations queried. Our main contribution is a simple, parallel decoding algorithm. Mutate Everything is capable of predicting the effect of all single and double mutations in one forward pass. It is even versatile enough to predict higher-order mutations with minimal computational overhead. We build Mutate Everything on top of ESM2 and AlphaFold, neither of which were trained to predict thermodynamic stability. We trained on the Mega-Scale cDNA proteolysis dataset and achieved state-of-the-art performance on single and higher-order mutations on S669, ProTherm, and ProteinGym datasets. Our code is available at https://github.com/jozhang97/MutateEverything.

In this paper, we present a system to train driving policies from experiences collected not just from the ego-vehicle, but all vehicles that it observes. This system uses the behaviors of other agents to create more diverse driving scenarios without collecting additional data. The main difficulty in learning from other vehicles is that there is no sensor information. We use a set of supervisory tasks to learn an intermediate representation that is invariant to the viewpoint of the controlling vehicle. This not only provides a richer signal at training time but also allows more complex reasoning during inference. Learning how all vehicles drive helps predict their behavior at test time and can avoid collisions. We evaluate this system in closed-loop driving simulations. Our system outperforms all prior methods on the public CARLA Leaderboard by a wide margin, improving driving score by 25 and route completion rate by 24 points.

We present cross-view transformers, an efficient attention-based model for map-view semantic segmentation from multiple cameras. Our architecture implicitly learns a mapping from individual camera views into a canonical map-view representation using a camera-aware cross-view attention mechanism. Each camera uses positional embeddings that depend on its intrinsic and extrinsic calibration. These embeddings allow a transformer to learn the mapping across different views without ever explicitly modeling it geometrically. The architecture consists of a convolutional image encoder for each view and cross-view transformer layers to infer a map-view semantic segmentation. Our model is simple, easily parallelizable, and runs in realtime. The presented architecture performs at state-of-the-art on the nuScenes dataset, with 4x faster inference speeds. Code is available at https://github.com/bradyz/cross_view_transformers.

How do we build a general and broad object detection system? We use all labels of all concepts ever annotated. These labels span diverse datasets with potentially inconsistent taxonomies. In this paper, we present a simple method for training a unified detector on multiple large-scale datasets. We use dataset-specific training protocols and losses, but share a common detection architecture with dataset-specific outputs. We show how to automatically integrate these dataset-specific outputs into a common semantic taxonomy. In contrast to prior work, our approach does not require manual taxonomy reconciliation. Experiments show our learned taxonomy outperforms a expert-designed taxonomy in all datasets. Our multi-dataset detector performs as well as dataset-specific models on each training domain, and can generalize to new unseen dataset without fine-tuning on them. Code is available at https://github.com/xingyizhou/UniDet.

We present a novel transformer-based architecture for global multi-object tracking. Our network takes a short sequence of frames as input and produces global trajectories for all objects. The core component is a global tracking transformer that operates on objects from all frames in the sequence. The transformer encodes object features from all frames, and uses trajectory queries to group them into trajectories. The trajectory queries are object features from a single frame and naturally produce unique trajectories. Our global tracking transformer does not require intermediate pairwise grouping or combinatorial association, and can be jointly trained with an object detector. It achieves competitive performance on the popular MOT17 benchmark, with 75.3 MOTA and 59.1 HOTA. More importantly, our framework seamlessly integrates into state-of-the-art large-vocabulary detectors to track any objects. Experiments on the challenging TAO dataset show that our framework consistently improves upon baselines that are based on pairwise association, outperforming published work by a significant 7.7 tracking mAP. Code is available at https://github.com/xingyizhou/GTR.

Our world offers a never-ending stream of visual stimuli, yet today’s vision systems only accurately recognize patterns within a few seconds. These systems understand the present, but fail to contextualize it in past or future events. In this paper, we study long-form video understanding. We introduce a framework for modeling long-form videos and develop evaluation protocols on large-scale datasets. We show that existing state-of-the-art short-term models are limited for long-form tasks. A novel object-centric transformer-based video recognition architecture performs significantly better on 7 diverse tasks. It also outperforms comparable state-of-the-art on the AVA dataset.

Three-dimensional objects are commonly represented as 3D boxes in a point-cloud. This representation mimics the well-studied image-based 2D bounding-box detection but comes with additional challenges. Objects in a 3D world do not follow any particular orientation, and box-based detectors have difficulties enumerating all orientations or fitting an axis-aligned bounding box to rotated objects. In this paper, we instead propose to represent, detect, and track 3D objects as points. Our framework, CenterPoint, first detects centers of objects using a keypoint detector and regresses to other attributes, including 3D size, 3D orientation, and velocity. In a second stage, it refines these estimates using additional point features on the object. In CenterPoint, 3D object tracking simplifies to greedy closest-point matching. The resulting detection and tracking algorithm is simple, efficient, and effective. CenterPoint achieved state-of-the-art performance on the nuScenes benchmark for both 3D detection and tracking, with 65.5 NDS and 63.8 AMOTA for a single model. On the Waymo Open Dataset, Center-Point outperforms all previous single model methods by a large margin and ranks first among all Lidar-only submissions. The code and pretrained models are available at https://github.com/tianweiy/CenterPoint.

We learn an interactive vision-based driving policy from pre-recorded driving logs via a model-based approach. A forward model of the world supervises a driving policy that predicts the outcome of any potential driving trajectory. To support learning from pre-recorded logs, we assume that the world is on rails, meaning neither the agent nor its actions influence the environment. This assumption greatly simplifies the learning problem, factorizing the dynamics into a non-reactive world model and a low-dimensional and compact forward model of the ego-vehicle. Our approach computes action-values for each training trajectory using a tabular dynamic-programming evaluation of the Bellman equations; these action-values in turn supervise the final vision-based driving policy. Despite the world-on-rails assumption, the final driving policy acts well in a dynamic and reactive world. It outperforms imitation learning as well as model-based and model-free reinforcement learning on the challenging CARLA NoCrash benchmark. It is also an order of magnitude more sample-efficient than state-of-the-art model-free reinforcement learning techniques on navigational tasks in the ProcGen benchmark.

Lidar-based sensing drives current autonomous vehicles. Despite rapid progress, current Lidar sensors still lag two decades behind traditional color cameras in terms of resolution and cost. For autonomous driving, this means that large objects close to the sensors are easily visible, but far-away or small objects comprise only one measurement or two. This is an issue, especially when these objects turn out to be driving hazards. On the other hand, these same objects are clearly visible in onboard RGB sensors. In this work, we present an approach to seamlessly fuse RGB sensors into Lidar-based 3D recognition. Our approach takes a set of 2D detections to generate dense 3D virtual points to augment an otherwise sparse 3D point cloud. These virtual points naturally integrate into any standard Lidar-based 3D detectors along with regular Lidar measurements. The resulting multi-modal detector is simple and effective. Experimental results on the large-scale nuScenes dataset show that our framework improves a strong CenterPoint baseline by a significant $6.6$ mAP, and outperforms competing fusion approaches. Code and more visualizations are available at https://tianweiy.github.io/mvp/

Training competitive deep video models is an order of magnitude slower than training their counterpart image models. Slow training causes long research cycles, which hinders progress in video understanding research. Following standard practice for training image models, video model training has used a fixed mini-batch shape: a specific number of clips, frames, and spatial size. However, what is the optimal shape? High resolution models perform well, but train slowly. Low resolution models train faster, but are less accurate. Inspired by multigrid methods in numerical optimization, we propose to use variable mini-batch shapes with different spatial-temporal resolutions that are varied according to a schedule. The different shapes arise from resampling the training data on multiple sampling grids. Training is accelerated by scaling up the mini-batch size and learning rate when shrinking the other dimensions. We empirically demonstrate a general and robust grid schedule that yields a significant out-of-the-box training speedup without a loss in accuracy for different models (I3D, non-local, SlowFast), datasets (Kinetics, Something-Something, Charades), and training settings (with and without pre-training, 128 GPUs or 1 GPU). As an illustrative example, the proposed multigrid method trains a ResNet-50 SlowFast network 4.5x faster (wall-clock time, same hardware) while also improving accuracy (+0.8% absolute) on Kinetics-400 compared to baseline training. Code is available online.

To understand the world, we humans constantly need to relate the present to the past, and put events in context. In this paper, we enable existing video models to do the same. We propose a long-term feature bank—supportive information extracted over the entire span of a video—to augment state-of-the-art video models that otherwise would only view short clips of 2-5 seconds. Our experiments demonstrate that augmenting 3D convolutional networks with a long-term feature bank yields state-of-the-art results on three challenging video datasets: AVA, EPIC-Kitchens, and Charades. Code is available online.

With the advent of deep learning, object detection drifted from a bottom-up to a top-down recognition problem. State of the art algorithms enumerate a near-exhaustive list of object locations and classify each into: object or not. In this paper, we show that bottom-up approaches still perform competitively. We detect four extreme points (top-most, left-most, bottom-most, right-most) and one center point of objects using a standard keypoint estimation network. We group the five keypoints into a bounding box if they are geometrically aligned. Object detection is then a purely appearance-based keypoint estimation problem, without region classification or implicit feature learning. The proposed method performs on-par with the state-of-the-art region based detection methods, with a bounding box AP of 43.7% on COCO test-dev. In addition, our estimated extreme points directly span a coarse octagonal mask, with a COCO Mask AP of 18.9%, much better than the Mask AP of vanilla bounding boxes. Extreme point guided segmentation further improves this to 34.6% Mask AP.

Vehicle 3D extents and trajectories are critical cues for predicting the future location of vehicles and planning future agent ego-motion based on those predictions. In this paper, we propose a novel online framework for 3D vehicle detection and tracking from monocular videos. The framework can not only associate detections of vehicles in motion over time, but also estimate their complete 3D bounding box information from a sequence of 2D images captured on a moving platform. Our method leverages 3D box depth-ordering matching for robust instance association and utilizes 3D trajectory prediction for re-identification of occluded vehicles. We also design a motion learning module based on an LSTM for more accurate long-term motion extrapolation. Our experiments on simulation, KITTI, and Argoverse datasets show that our 3D tracking pipeline offers robust data association and tracking. On Argoverse, our image-based method is significantly better for tracking 3D vehicles within 30 meters than the LiDAR-centric baseline methods.

Convolutions on monocular dash cam videos capture spatial invariances in the image plane but do not explicitly reason about distances and depth. We propose a simple transformation of observations into a bird's eye view, also known as plan view, for end-to-end control. We detect vehicles and pedestrians in the first person view and project them into an overhead plan view. This representation provides an abstraction of the environment from which a deep network can easily deduce the positions and directions of entities. Additionally, the plan view enables us to leverage advances in 3D object detection in conjunction with deep policy learning. We evaluate our monocular plan view network on the photo-realistic Grand Theft Auto V simulator. A network using both a plan view and front view causes less than half as many collisions as previous detection-based methods and an order of magnitude fewer collisions than pure pixel-based policies.

Deep networks are extremely hungry for data. They devour hundreds of thousands of labeled images to learn robust and semantically meaningful feature representations. Current networks are so data hungry that collecting labeled data has become as important as designing the networks themselves. Unfortunately, manual data collection is both expensive and time consuming. We present an alternative, and show how ground truth labels for many vision tasks are easily extracted from video games in real time as we play them. We interface the popular Microsoft® DirectX® rendering API, and inject specialized rendering code into the game as it is running. This code produces ground truth labels for instance segmentation, semantic labeling, depth estimation, optical flow, intrinsic image decomposition, and instance tracking. Instead of labeling images, a researcher now simply plays video games all day long. Our method is general and works on a wide range of video games. We collected a dataset of 220k training images, and 60k test images across 3 video games, and evaluate state of the art optical flow, depth estimation and intrinsic image decomposition algorithms. Our video game data is visually closer to real world images, than other synthetic dataset.

Training robust deep video representations has proven to be much more challenging than learning deep image representations. This is in part due to the enormous size of raw video streams and the high temporal redundancy; the true and interesting signal is often drowned in too much irrelevant data. Motivated by that the superfluous information can be reduced by up to two orders of magnitude by video compression (using H.264, HEVC, etc.), we propose to train a deep network directly on the compressed video. This representation has a higher information density, and we found the training to be easier. In addition, the signals in a compressed video provide free, albeit noisy, motion information. We propose novel techniques to use them effectively. Our approach is about 4.6 times faster than Res3D and 2.7 times faster than ResNet-152. On the task of action recognition, our approach outperforms all the other methods on the UCF-101, HMDB-51, and Charades dataset.

Deep embeddings answer one simple question: How similar are two images? Learning these embeddings is the bedrock of verification, zero-shot learning, and visual search. The most prominent approaches optimize a deep convolutional network with a suitable loss function, such as contrastive loss or triplet loss. While a rich line of work focuses solely on the loss functions, we show in this paper that selecting training examples plays an equally important role. We propose distance weighted sampling, which selects more informative and stable examples than traditional approaches. In addition, we show that a simple margin based loss is sufficient to outperform all other loss functions. We evaluate our approach on the Stanford Online Products, CAR196, and the CUB200-2011 datasets for image retrieval and clustering, and on the LFW dataset for face verification. Our method achieves state-of-the-art performance on all of them.

We present an unsupervised visual feature learning algorithm driven by context-based pixel prediction. By analogy with auto-encoders, we propose Context Encoders - a convolutional neural network trained to generate the contents of an arbitrary image region conditioned on its surroundings. In order to succeed at this task, context encoders need to both understand the content of the entire image, as well as produce a plausible hypothesis for the missing part(s). When training context encoders, we have experimented with both a standard pixel-wise reconstruction loss, as well as a reconstruction plus an adversarial loss. The latter produces much sharper results because it can better handle multiple modes in the output. We found that a context encoder learns a representation that captures not just appearance but also the semantics of visual structures. We quantitatively demonstrate the effectiveness of our learned features for CNN pre-training on classification, detection, and segmentation tasks. Furthermore, context encoders can be used for semantic inpainting tasks, either stand-alone or as initialization for non-parametric methods.

Discriminative deep learning approaches have shown impressive results for problems where human-labeled ground truth is plentiful, but what about tasks where labels are difficult or impossible to obtain? This paper tackles one such problem: establishing dense visual correspondence across different object instances. For this task, although we do not know what the ground-truth is, we know it should be consistent across instances of that category. We exploit this consistency as a supervisory signal to train a convolutional neural network to predict cross-instance correspondences between pairs of images depicting objects of the same category. For each pair of training images we find an appropriate 3D CAD model and render two synthetic views to link in with the pair, establishing a correspondence flow 4-cycle. We use ground-truth synthetic-to-synthetic correspondences, provided by the rendering engine, to train a ConvNet to predict synthetic-to-real, real-to-real and real-to-synthetic correspondences that are cycle-consistent with the ground-truth. At test time, no CAD models are required. We demonstrate that our end-to-end trained ConvNet supervised by cycle-consistency outperforms state-of-the-art pairwise matching methods in correspondence-related tasks.

We present an approach for highly accurate bottom-up object segmentation. Given an image, the approach rapidly generates a set of regions that delineate candidate objects in the image. The key idea is to train an ensemble of figure-ground segmentation models. The ensemble is trained jointly, enabling individual models to specialize and complement each other. We reduce ensemble training to a sequence of uncapacitated facility location problems and show that highly accurate segmentation ensembles can be trained by combinatorial optimization. The training procedure jointly optimizes the size of the ensemble, its composition, and the parameters of incorporated models, all for the same objective. The ensembles operate on elementary image features, enabling rapid image analysis. Extensive experiments demonstrate that the presented approach outperforms prior object proposal algorithms by a significant margin, while having the lowest running time. The trained ensembles generalize across datasets, indicating that the presented approach is capable of learning a generally applicable model of bottom-up segmentation.

We present an approach to learn a dense pixel-wise labeling from image-level tags. Each image-level tag imposes constraints on the output labeling of a Convolutional Neural Network (CNN) classifier. We propose Constrained CNN (CCNN), a method which uses a novel loss function to optimize for any set of linear constraints on the output space (i.e. predicted label distribution) of a CNN. Our loss formulation is easy to optimize and can be incorporated directly into standard stochastic gradient descent optimization. The key idea is to phrase the training objective as a biconvex optimization for linear models, which we then relax to nonlinear deep networks. Extensive experiments demonstrate the generality of our new learning framework. The constrained loss yields state-of-the-art results on weakly supervised semantic image segmentation. We further demonstrate that adding slightly more supervision can greatly improve the performance of the learning algorithm.

We propose a data-driven approach for intrinsic image decomposition, which is the process of inferring the confounding factors of reflectance and shading in an image. We pose this as a two-stage learning problem. First, we train a model to predict relative reflectance ordering between image patches ('brighter', 'darker', 'same') from large-scale human annotations, producing a data-driven reflectance prior. Second, we show how to naturally integrate this learned prior into existing energy minimization frame-works for intrinsic image decomposition. We compare our method to the state-of-the-art approach of Bell et al. [7] on both decomposition and image relighting tasks, demonstrating the benefits of the simple relative reflectance prior, especially for scenes under challenging lighting conditions.

What makes an image appear realistic? In this work, we are answering this question from a data-driven perspective by learning the perception of visual realism directly from large amounts of data. In particular, we train a Convolutional Neural Network (CNN) model that distinguishes natural photographs from automatically generated composite images. The model learns to predict visual realism of a scene in terms of color, lighting and texture compatibility, without any human annotations pertaining to it. Our model outperforms previous works that rely on hand-crafted heuristics, for the task of classifying realistic vs. unrealistic photos. Furthermore, we apply our learned model to compute optimal parameters of a compositing method, to maximize the visual realism score predicted by our CNN model. We demonstrate its advantage against existing methods via a human perception study.

Dense random fields are models in which all pairs of variables are directly connected by pairwise potentials. It has recently been shown that mean field inference in dense random fields can be performed efficiently and that these models enable significant accuracy gains in computer vision applications. However, parameter estimation for dense random fields is still poorly understood. In this paper, we present an efficient algorithm for learning parameters in dense random fields. All parameters are estimated jointly, thus capturing dependencies between them. We show that gradients of a variety of loss functions over the mean field marginals can be computed efficiently. The resulting algorithm learns parameters that directly optimize the performance of mean field inference in the model. As a supporting result, we present an efficient inference algorithm for dense random fields that is guaranteed to converge.

Saliency estimation has become a valuable tool in image processing. Yet, existing approaches exhibit considerable variation in methodology, and it is often difficult to attribute improvements in result quality to specific algorithm properties. In this paper we reconsider some of the design choices of previous methods and propose a conceptually clear and intuitive algorithm for contrast-based saliency estimation. Our algorithm consists of four basic steps. First, our method decomposes a given image into compact, perceptually homogeneous elements that abstract unnecessary detail. Based on this abstraction we compute two measures of contrast that rate the uniqueness and the spatial distribution of these elements. From the element contrast we then derive a saliency measure that produces a pixel-accurate saliency map which uniformly covers the objects of interest and consistently separates fore- and background. We show that the complete contrast and saliency estimation can be formulated in a unified way using high-dimensional Gaussian filters. This contributes to the conceptual simplicity of our method and lends itself to a highly efficient implementation with linear complexity. In a detailed experimental evaluation we analyze the contribution of each individual feature and show that our method outperforms all state-of-the-art approaches.

Most state-of-the-art techniques for multi-class image segmentation and labeling use conditional random fields defined over pixels or image regions. While region- level models often feature dense pairwise connectivity, pixel-level models are con- siderably larger and have only permitted sparse graph structures. In this paper, we consider fully connected CRF models defined on the complete set of pixels in an image. The resulting graphs have billions of edges, making traditional inference algorithms impractical. Our main contribution is a highly efficient approximate inference algorithm for fully connected CRF models in which the pairwise edge potentials are defined by a linear combination of Gaussian kernels. Our experi- ments demonstrate that dense connectivity at the pixel level substantially improves segmentation and labeling accuracy.

We introduce gesture controllers , a method for animating the body language of avatars engaged in live spoken conversation. A gesture controller is an optimal-policy controller that schedules gesture animations in real time based on acoustic features in the user's speech. The controller consists of an inference layer, which infers a distribution over a set of hidden states from the speech signal, and a control layer, which selects the optimal motion based on the inferred state distribution. The inference layer, consisting of a specialized conditional random field, learns the hidden structure in body language style and associates it with acoustic features in speech. The control layer uses reinforcement learning to construct an optimal policy for selecting motion clips from a distribution over the learned hidden states. The modularity of the proposed method allows customization of a character's gesture repertoire, animation of non-human characters, and the use of additional inputs such as speech recognition or direct user control.

We present a novel, integrated system for content-aware video retargeting. A simple and interactive framework combines key frame based constraint editing with numerous automatic algorithms for video analysis. This combination gives content producers high level control of the retargeting process. The central component of our framework is a non-uniform, pixel-accurate warp to the target resolution which considers automatic as well as interactively defined features. Automatic features comprise video saliency, edge preservation at the pixel resolution, and scene cut detection to enforce bilateral temporal coherence. Additional high level constraints can be added by the producer to guarantee a consistent scene composition across arbitrary output formats. For high quality video display we adopted a 2D version of EWA splatting eliminating aliasing artifacts known from previous work. Our method seamlessly integrates into postproduction and computes the reformatting in real-time. This allows us to retarget annotated video streams at a high quality to arbitary aspect ratios while retaining the intended cinematographic scene composition. For evaluation we conducted a user study which revealed a strong viewer preference for our method.