Abstract Large Language Models (LLMs) exhibit In-Context Learning (ICL), which enables the model to perform new tasks conditioning only on the examples provided in the context without updating the model’s weights. While ICL offers fast adaptation across natural language tasks and domains, its emergence is less straightforward for modalities beyond text. In this work, we systematically uncover properties present in LLMs that support the emergence of ICL for autoregressive models and various modalities by promoting the learning of the mechanisms needed for ICL. We identify exact token repetitions in the training data sequences as an important factor for ICL. Such repetitions further improve stability and reduce transiency in ICL performance. We analyse in detail the training dynamics of such data sequences and explain how token repetitions enhance the ICL learning mechanisms. Moreover, we emphasise the importance of the training task difficulty for the emergence of ICL. Finally, by applying our novel insights on ICL emergence, we unlock ICL capabilities across various visual datasets used for few-shot classification, and confirm the generalisability of our insights to much harder real-world examples of large-scale object classification, and a more challenging EEG classification task. Code is available at https://github.com/jelenab98/unlocking_icl

3D scene generation has quickly become a challenging new research direction, fueled by consistent improvements of 2D generative diffusion models. Current methods generate scenes by iteratively stitching newly generated images with existing geometry, using pre-trained monocular depth estimators to lift the generated images to 3D. The predicted depth is fused with the existing scene representation through various alignment operations. In this work, we make two fundamental contributions to the field of 3D scene generation. First, we note that lifting images to 3D with a monocular depth estimation model is suboptimal as it ignores the geometry of the existing scene, thus prompting the need for alignment. We introduce a depth completion model to directly learn the 3D fusion process, resulting in improved geometric coherence of generated scenes. Second, we introduce a new benchmark to evaluate the geometric accuracy of scene generation methods. We show that the commonly used CLIP score between scene prompts and images is unsuitable for measuring the geometric quality of a scene and introduce a depth-based metric. Our benchmark thus offers an additional dimension to gauge the quality of generated scenes.

We propose Flash3D, a method for scene reconstruction and novel view synthesis from a single image which is both very generalisable and efficient. For generalisability, we start from a 'foundation' model for monocular depth estimation and extend it to a full 3D shape and appearance reconstructor. For efficiency, we base this extension on feed-forward Gaussian Splatting. Specifically, we predict a first layer of 3D Gaussians at the predicted depth, and then add additional layers of Gaussians that are offset in space, allowing the model to complete the reconstruction behind occlusions and truncations. Flash3D is very efficient, trainable on a single GPU in a day, and thus accessible to most researchers. It achieves state-of-the-art results when trained and tested on RealEstate10k. When transferred to unseen datasets like NYU it outperforms competitors by a large margin. More impressively, when transferred to KITTI, Flash3D achieves better PSNR than methods trained specifically on that dataset. In some instances, it even outperforms recent methods that use multiple views as input. Code, models, demo, and more results are available at https://www.robots.ox.ac.uk/~vgg/research/flash3d/.

Unsupervised panoptic segmentation aims to partition an image into semantically meaningful regions and distinct object instances without training on manually annotated data. In contrast to prior work on unsupervised panoptic scene understanding, we eliminate the need for object-centric training data, enabling the unsupervised understanding of complex scenes. To that end, we present the first unsupervised panoptic method that directly trains on scene-centric imagery. In particular, we propose an approach to obtain high-resolution panoptic pseudo labels on complex scene-centric data, combining visual representations, depth, and motion cues. Utilizing both pseudo-label training and a panoptic self-training strategy yields a novel approach that accurately predicts panoptic segmentation of complex scenes without requiring any human annotations. Our approach significantly improves panoptic quality, e.g., surpassing the recent state of the art in unsupervised panoptic segmentation on Cityscapes by 9.4 % points in PQ.

We propose a new "Unbiased through Textual Description (UTD)" video benchmark based on unbiased subsets of existing video classification and retrieval datasets to enable a more robust assessment of video understanding capabilities. Namely, we tackle the problem that current video benchmarks may suffer from different representation biases, e.g., object bias or single-frame bias, where mere recognition of objects or utilization of only a single frame is sufficient for correct prediction. We leverage VLMs and LLMs to analyze and debias benchmarks from such representation biases. Specifically, we generate frame-wise textual descriptions of videos, filter them for specific information (e.g. only objects) and leverage them to examine representation biases across three dimensions: 1) concept bias — determining if a specific concept (e.g., objects) alone suffice for prediction; 2) temporal bias — assessing if temporal information contributes to prediction; and 3) common sense vs. dataset bias — evaluating whether zero-shot reasoning or dataset correlations contribute to prediction. We conduct a systematic analysis of 12 popular video classification and retrieval datasets and create new object-debiased test splits for these datasets. Moreover, we benchmark 30 state-of-the-art video models on original and debiased splits and analyze biases in the models. To facilitate the future development of more robust video understanding benchmarks and models, we release: "UTD-descriptions", a dataset with our rich structured descriptions for each dataset, and "UTD-splits", a dataset of object-debiased test splits.1

We present VGGT, a feed-forward neural network that directly infers all key 3D attributes of a scene, including camera parameters, point maps, depth maps, and 3D point tracks, from one, a few, or hundreds of its views. This approach is a step forward in 3D computer vision, where models have typically been constrained to and specialized for single tasks. It is also simple and efficient, reconstructing images in under one second, and still outperforming alternatives that require post-processing with visual geometry optimization techniques. The network achieves state-of-the-art results in multiple 3D tasks, including camera parameter estimation, multi-view depth estimation, dense point cloud reconstruction, and 3D point tracking. We also show that using pretrained VGGT as a feature backbone significantly enhances downstream tasks, such as non-rigid point tracking and feed-forward novel view synthesis. Code and models are publicly available at https://github.com/facebookresearch/vggt.

Estimating camera motion and intrinsics from casual videos is a core challenge in computer vision. Traditional bundle-adjustment based methods, such as SfM and SLAM, struggle to perform reliably on arbitrary data. Although specialized SfM approaches have been developed for handling dynamic scenes, they either require intrinsics or computationally expensive test-time optimization and often fall short in performance. Recently, methods like Dust3r have reformulated the SfM problem in a more data-driven way. While such techniques show promising results, they are still 1) not robust towards dynamic objects and 2) require labeled data for supervised training. As an alternative, we propose AnyCam, a fast transformer model that directly estimates camera poses and intrinsics from a dynamic video sequence in feed-forward fashion. Our intuition is that such a network can learn strong priors over realistic camera poses. To scale up our training, we rely on an uncertainty-based loss formulation and pre-trained depth and flow networks instead of motion or trajectory supervision. This allows us to use diverse, unlabelled video datasets obtained mostly from YouTube. Additionally, we ensure that the predicted trajectory does not accumulate drift over time through a lightweight trajectory refinement step. We test AnyCam on established datasets, where it delivers accurate camera poses and intrinsics both qualitatively and quantitatively. Furthermore, even with trajectory refinement, Any-Cam is significantly faster than existing works for SfM in dynamic settings. Finally, by combining camera information, uncertainty, and depth, our model can produce high-quality 4D pointclouds. For more details and code, please check out our project page: fwmb.github.io/anycam

We present FLARE, a feed-forward model designed to infer high-quality camera poses and 3D geometry from uncalibrated sparse-view images (i.e., as few as 2-8 inputs), which is a challenging yet practical setting in real-world applications. Our solution features a cascaded learning paradigm with camera pose serving as the critical bridge, recognizing its essential role in mapping 3D structures onto 2D image planes. Concretely, FLARE starts with camera pose estimation, whose results condition the subsequent learning of geometric structure and appearance, optimized through the objectives of geometry reconstruction and novel-view synthesis. Utilizing large-scale public datasets for training, our method delivers state-of-the-art performance in the tasks of pose estimation, geometry reconstruction, and novel view synthesis, while maintaining the inference efficiency (i.e., less than 0.5 seconds). The project page and code can be found at: https://zhanghe3z.github.io/FLARE/

An important challenge when using computer vision models in the real world is to evaluate their performance in potential out-of-distribution (OOD) scenarios. While simple synthetic corruptions are commonly applied to test OOD robustness, they often fail to capture nuisance shifts that occur in the real world. Recently, diffusion models have been applied to generate realistic images for benchmarking, but they are restricted to binary nuisance shifts. In this work, we introduce CNS-Bench, a Continuous Nuisance Shift Benchmark to quantify OOD robustness of image classifiers for continuous and realistic generative nuisance shifts. CNS-Bench allows generating a wide range of individual nuisance shifts in continuous severities by applying LoRA adapters to diffusion models. To address failure cases, we propose a filtering mechanism that outperforms previous methods, thereby enabling reliable benchmarking with generative models. With the proposed benchmark, we perform a large-scale study to evaluate the robustness of more than 40 classifiers under various nuisance shifts. Through carefully designed comparisons and analyses, we find that model rankings can change for varying shifts and shift scales, which cannot be captured when applying common binary shifts. Additionally, we show that evaluating the model performance on a continuous scale allows the identification of model failure points, providing a more nuanced understanding of model robustness. Project page including code and data: https://genintel.github.io/CNS.

We address the challenge of generating 3D worlds from textual descriptions. We propose SynCity, a training- and optimization-free approach, which leverages the geometric precision of pre-trained 3D generative models and the artistic versatility of 2D image generators to create large, high-quality 3D spaces. While most 3D generative models are object-centric and cannot generate large-scale worlds, we show how 3D and 2D generators can be combined to generate ever-expanding scenes. Through a tile-based approach, we allow fine-grained control over the layout and the appearance of scenes. The world is generated tile-by-tile, and each new tile is generated within its world-context and then fused with the scene. SynCity generates compelling and immersive scenes that are rich in detail and diversity.

Semantic scene completion (SSC) aims to infer both the 3D geometry and semantics of a scene from single images. In contrast to prior work on SSC that heavily relies on expensive ground-truth annotations, we approach SSC in an unsupervised setting. Our novel method, SceneDINO, adapts techniques from self-supervised representation learning and 2D unsupervised scene understanding to SSC. Our training exclusively utilizes multi-view consistency self-supervision without any form of semantic or geometric ground truth. Given a single input image, SceneDINO infers the 3D geometry and expressive 3D DINO features in a feed-forward manner. Through a novel 3D feature distillation approach, we obtain unsupervised 3D semantics. In both 3D and 2D unsupervised scene understanding, SceneDINO reaches state-of-the-art segmentation accuracy. Linear probing our 3D features matches the segmentation accuracy of a current supervised SSC approach. Additionally, we showcase the domain generalization and multi-view consistency of SceneDINO, taking the first steps towards a strong foundation for single image 3D scene understanding.

We introduce Puppet-Master, an interactive video generator that captures the internal, part-level motion of objects, serving as a proxy for modeling object dynamics universally. Given an image of an object and a set of "drags" specifying the trajectory of a few points on the object, the model synthesizes a video where the object's parts move accordingly. To build Puppet-Master, we extend a pre-trained image-to-video generator to encode the input drags. We also propose all-to-first attention, an alternative to conventional spatial attention that mitigates artifacts caused by fine-tuning a video generator on out-of-domain data. The model is fine-tuned on Objaverse-Animation-HQ, a new dataset of curated part-level motion clips obtained by rendering synthetic 3D animations. Unlike real videos, these synthetic clips avoid confounding part-level motion with overall object and camera motion. We extensively filter sub-optimal animations and augment the synthetic renderings with meaningful drags that emphasize the internal dynamics of objects. We demonstrate that Puppet-Master learns to generate part-level motions, unlike other motion-conditioned video generators that primarily move the object as a whole. Moreover, Puppet-Master generalizes well to out-of-domain real images, outperforming existing methods on real-world benchmarks in a zero-shot manner.

We present Stable Virtual Camera (Seva), a generalist diffusion model that creates novel views of a scene, given any number of input views and target cameras. Existing works struggle to generate either large viewpoint changes or temporally smooth samples, while relying on specific task configurations. Our approach overcomes these limitations through simple model design, optimized training recipe, and flexible sampling strategy that generalize across view synthesis tasks at test time. As a result, our samples maintain high consistency without requiring additional 3D representation-based distillation, thus streamlining view synthesis in the wild. Furthermore, we show that our method can generate high-quality videos lasting up to half a minute with seamless loop closure. Extensive benchmarking demonstrates that Seva outperforms existing methods across different datasets and settings. Project page with code and model: https://stable-virtual-camera.github.io/.

3D semantic scene understanding is a fundamental challenge in computer vision. It enables mobile agents to autonomously plan and navigate arbitrary environments. SSC formalizes this challenge as jointly estimating dense geometry and semantic information from sparse observations of a scene. Current methods for SSC are generally trained on 3D ground truth based on aggregated LiDAR scans. This process relies on special sensors and annotation by hand which are costly and do not scale well. To overcome this issue, our work presents the first self-supervised approach to SSC called S4C that does not rely on 3D ground truth data. Our proposed method can reconstruct a scene from a single image and only relies on videos and pseudo segmentation ground truth generated from off-the-shelf image segmentation network during training. Unlike existing methods, which use discrete voxel grids, we represent scenes as implicit semantic fields. This formulation allows querying any point within the camera frustum for occupancy and semantic class. Our architecture is trained through rendering-based self-supervised losses. Nonetheless, our method achieves performance close to fully supervised state-of-the-art methods. Additionally, our method demonstrates strong generalization capabilities and can synthesize accurate segmentation maps for far away viewpoints.

We present Farm3D, a method for learning category-specific 3D reconstructors for articulated objects, relying solely on “free” virtual supervision from a pre-trained 2D diffusion-based image generator. Recent approaches can learn a monocular network that predicts the 3D shape, albedo, illumination, and viewpoint of any object occurrence, given a collection of single-view images of an object category. However, these approaches heavily rely on manually curated clean training data, which are expensive to obtain. We propose a framework that uses an image generator, such as Stable Diffusion, to generate synthetic training data that are sufficiently clean and do not require further manual curation, enabling the learning of such a reconstruction network from scratch. Additionally, we incorporate the diffusion model as a score to enhance the learning process. The idea involves randomizing certain aspects of the reconstruction, such as viewpoint and illumination, generating virtual views of the reconstructed 3D object, and allowing the 2D network to assess the quality of the resulting image, thus providing feedback to the reconstructor. Unlike work based on distillation, which produces a single 3D asset for each textual prompt, our approach yields a monocular reconstruction network capable of outputting a controllable 3D asset from any given image, whether real or generated, in a single forward pass in a matter of seconds. Our network can be used for analysis, including monocular reconstruction, or for synthesis, generating articulated assets for real-time applications such as video games. The code can be found on the project page at https://farm3d.github.io/.

Learning 3D models of all animals in nature requires massively scaling up existing solutions. With this ultimate goal in mind, we develop 3D-Fauna, an approach that learns a pan-category deformable 3D animal model for more than 100 animal species jointly. One crucial bottle-neck of modeling animals is the limited availability of training data, which we overcome by learning our model from 2D Internet images. We show that prior approaches, which are category-specific, fail to generalize to rare species with limited training images. We address this challenge by introducing the Semantic Bank of Skinned Models (SBSM), which automatically discovers a small set of base animal shapes by combining geometric inductive priors with semantic knowledge implicitly captured by an off-the-shelf self-supervised feature extractor. To train such a model, we also contribute a new large-scale dataset of diverse animal species. At inference time, given a single image of any quadruped animal, our model reconstructs an articulated 3D mesh in a feed-forward manner in seconds.

We introduce the Splatter Image, an ultra-efficient approach for monocular 3D object reconstruction. Splatter Image is based on Gaussian Splatting, which allows fast and high-quality reconstruction of 3D scenes from multiple images. We apply Gaussian Splatting to monocular reconstruction by learning a neural network that, at test time, performs reconstruction in a feed-forward manner, at 38 FPS. Our main innovation is the surprisingly straightforward design of this network, which, using 2D operators, maps the input image to one 3D Gaussian per pixel. The resulting set of Gaussians thus has the form an image, the Splatter Image. We further extend the method take several images as input via cross-view attention. Owning to the speed of the renderer (588 FPS), we use a single GPU for training while generating entire images at each iteration to optimize perceptual metrics like LPIPS. On several synthetic, real, multi-category and large-scale benchmark datasets, we achieve better results in terms of PSNR, LPIPS, and other metries while training and evaluating much faster than prior works. Code, models and more results are available at https://szymanowiczs.github.io/splatter-image.

Structure-from-motion (SfM) is a longstanding problem in the computer vision community, which aims to reconstruct the camera poses and 3D structure of a scene from a set of unconstrained 2D images. Classical frameworks solve this problem in an incremental manner by detecting and matching keypoints, registering images, triangulating 3D points, and conducting bundle adjustment. Recent research efforts have predominantly revolved around harnessing the power of deep learning techniques to enhance specific elements (e.g., keypoint matching), but are still based on the original, non-differentiable pipeline. Instead, we propose a new deep pipeline VGGSfM, where each component is fully differentiable and thus can be trained in an end-to-end manner. To this end, we introduce new mechanisms and simplifications. First, we build on recent advances in deep 2D point tracking to extract reliable pixel-accurate tracks, which eliminates the need for chaining pairwise matches. Furthermore, we recover all cameras simultaneously based on the image and track features instead of gradually registering cameras. Finally, we optimise the cameras and triangulate 3D points via a differentiable bundle adjustment layer. We attain state-of-the-art performance on three popular datasets, CO3D, IMC Phototourism, and ETH3D.

Diffusion models have recently revolutionized the field of image synthesis due to their ability to generate photorealistic images. However, one of the major drawbacks of diffusion models is that the image generation process is costly. A large image-to-image network has to be applied many times to iteratively refine an image from random noise. While many recent works propose techniques to reduce the number of required steps, they generally treat the underlying denoising network as a black box. In this work, we investigate the behavior of the layers within the network and find that 1) the layers' output changes smoothly over time, 2) the layers show distinct patterns of change, and 3) the change from step to step is often very small. We hypothesize that many layer computations in the denoising network are redundant. Leveraging this, we introduce block caching, in which we reuse outputs from layer blocks of previous steps to speed up inference. Furthermore, we propose a technique to automatically determine caching schedules based on each block's changes over timesteps. In our experiments, we show through FID, human evaluation and qualitative analysis that Block Caching allows to generate images with higher visual quality at the same computational cost. We demonstrate this for different state-of-the-art models (LDM and EMU) and solvers (DDIM and DPM). Project page: fwmb.github.io/blockcaching

Most text-to-3D generators build upon off-the-shelf text-to-image models trained on billions of images. They use variants of Score Distillation Sampling (SDS), which is slow, somewhat unstable, and prone to artifacts. A mitigation is to fine-tune the 2D generator to be multi-view aware, which can help distillation or can be combined with reconstruction networks to output 3D objects directly. In this paper, we further explore the design space of text-to-3D models. We significantly improve multi-view generation by considering video instead of image generators. Combined with a 3D reconstruction algorithm which, by using Gaussian splatting, can optimize a robust image-based loss, we directly produce high-quality 3D outputs from the generated views. Our new method, IM-3D, reduces the number of evaluations of the 2D generator network 10-100$\times$, resulting in a much more efficient pipeline, better quality, fewer geometric inconsistencies, and higher yield of usable 3D assets.

We consider the problem of segmenting objects in videos based on their motion and no other forms of supervision. Prior work has often approached this problem by using the principle of common fate, namely the fact that the motion of points that belong to the same object is strongly correlated. However, most authors have only considered instantaneous motion from optical flow. In this work, we present a way to train a segmentation network using long-term point trajectories as a supervisory signal to complement optical flow. The key difficulty is that long-term motion, unlike instantaneous motion, is difficult to model -- any parametric approximation is unlikely to capture complex motion patterns over long periods of time. We instead draw inspiration from subspace clustering approaches, proposing a loss function that seeks to group the trajectories into low-rank matrices where the motion of object points can be approximately explained as a linear combination of other point tracks. Our method outperforms the prior art on motion-based segmentation, which shows the utility of long-term motion and the effectiveness of our formulation.

Abstract Reconstructing models of the real world, including 3D geometry, appearance, and motion of real scenes, is essential for computer graphics and computer vision. It enables the synthesizing of photorealistic novel views, useful for the movie industry and AR/VR applications. It also facilitates the content creation necessary in computer games and AR/VR by avoiding laborious manual design processes. Further, such models are fundamental for intelligent computing systems that need to interpret real‐world scenes and actions to act and interact safely with the human world. Notably, the world surrounding us is dynamic, and reconstructing models of dynamic, non‐rigidly moving scenes is a severely underconstrained and challenging problem. This state‐of‐the‐art report (STAR) offers the reader a comprehensive summary of state‐of‐the‐art techniques with monocular and multi‐view inputs such as data from RGB and RGB‐D sensors, among others, conveying an understanding of different approaches, their potential applications, and promising further research directions. The report covers 3D reconstruction of general non‐rigid scenes and further addresses the techniques for scene decomposition, editing and controlling, and generalizable and generative modeling. More specifically, we first review the common and fundamental concepts necessary to understand and navigate the field and then discuss the state‐of‐the‐art techniques by reviewing recent approaches that use traditional and machine‐learning‐based neural representations, including a discussion on the newly enabled applications. The STAR is concluded with a discussion of the remaining limitations and open challenges.

Most of us are not experts in specific fields, such as ornithology. Nonetheless, we do have general image and language understanding capabilities that we use to match what we see to expert resources. This allows us to expand our knowledge and perform novel tasks without ad-hoc external supervision. On the contrary, machines have a much harder time consulting expert-curated knowledge bases unless trained specifically with that knowledge in mind. Thus, in this paper we consider a new problem: fine-grained image recognition without expert annotations, which we address by leveraging the vast knowledge available in web encyclopedias. First, we learn a model to describe the visual appearance of objects using non-expert image descriptions. We then train a fine-grained textual similarity model that matches image descriptions with documents on a sentence-level basis. We evaluate the method on two datasets (CUB-200 and Oxford-102 Flowers) and compare with several strong baselines and the state of the art in cross-modal retrieval. Code is available at: https://github.com/subhc/clever.

Incremental object detection (IOD) aims to train an object detector in phases, each with annotations for new object categories. As other incremental settings, IOD is subject to catastrophic forgetting, which is often addressed by techniques such as knowledge distillation (KD) and exem-plar replay (ER). However, KD and ER do not work well if applied directly to state-of-the-art transformer-based object detectors such as Deformable DETR [59] and UP-DETR [9]. In this paper, we solve these issues by proposing a ContinuaL DEtection TRansformer (CL-DETR), a new method for transformer-based IOD which enables effective usage of KD and ER in this context. First, we introduce a Detector Knowledge Distillation (DKD) loss, focusing on the most informative and reliable predictions from old versions of the model, ignoring redundant background predictions, and ensuring compatibility with the available ground-truth labels. We also improve ER by proposing a calibration strategy to preserve the label distribution of the training set, therefore better matching training and testing statistics. We conduct extensive experiments on COCO 2017 and demonstrate that CL-DETR achieves state-of-the-art results in the IOD setting.11Code: https://1yy.mpi-inf.mpg.de/CL-DETR/

We consider the problem of reconstructing a dynamic scene observed from a stereo camera. Most existing meth-ods for depth from stereo treat different stereo frames in-dependently, leading to temporally inconsistent depth pre-dictions. Temporal consistency is especially important for immersive AR or VR scenarios, where flickering greatly di-minishes the user experience. We propose DynamicStereo, a novel transformer-based architecture to estimate dispar-ity for stereo videos. The network learns to pool information from neighboring frames to improve the temporal consistency of its predictions. Our architecture is designed to process stereo videos efficiently through divided attention layers. We also introduce Dynamic Replica, a new bench-mark dataset containing synthetic videos of people and ani-mals in scanned environments, which provides complemen-tary training and evaluation data for dynamic stereo closer to real applications than existing datasets. Training with this dataset further improves the quality of predictions of our proposed DynamicStereo as well as prior methods. Finally, it acts as a benchmark for consistent stereo methods. Project page: https://dynamic-stereo.github.io/

Reconstructing the 3D shape of an object from a single RGB image is a long-standing problem in computer vision. In this paper, we propose a novel method for single-image 3D reconstruction which generates a sparse point cloud via a conditional denoising diffusion process. Our method takes as input a single RGB image along with its camera pose and gradually denoises a set of 3D points, whose positions are initially sampled randomly from a three-dimensional Gaussian distribution, into the shape of an object. The key to our method is a geometrically-consistent conditioning process which we call projection conditioning: at each step in the diffusion process, we project local image features onto the partially-denoised point cloud from the given camera pose. This projection conditioning process enables us to generate high-resolution sparse geometries that are well-aligned with the input image and can additionally be used to predict point colors after shape reconstruction. Moreover, due to the probabilistic nature of the diffusion process, our method is naturally capable of generating multiple different shapes consistent with a single input image. In contrast to prior work, our approach not only performs well on synthetic benchmarks but also gives large qualitative improvements on complex real-world data. Data and code are available at https://lukemelas.github.io/projectionconditioned-point-cloud-diffusion/.

We consider the problem of reconstructing a full 360° photographic model of an object from a single image of it. We do so by fitting a neural radiance field to the image, but find this problem to be severely ill-posed. We thus take an off-the-self conditional image generator based on diffusion and engineer a prompt that encourages it to “dream up” novel views of the object. Using the recent DreamFusion method, we fuse the given input view, the conditional prior, and other regularizers into a final, consistent reconstruction. We demonstrate state-of-the-art reconstruction results on benchmark images when compared to prior methods for monocular 3D reconstruction of objects. Qualitatively, our reconstructions provide a faithful match of the input view and a plausible extrapolation of its appearance and 3D shape, including to the side of the object not visible in the image.

Inferring a meaningful geometric scene representation from a single image is a fundamental problem in computer vision. Approaches based on traditional depth map prediction can only reason about areas that are visible in the image. Currently, neural radiance fields (NeRFs) can capture true 3D including color, but are too complex to be generated from a single image. As an alternative, we propose to predict an implicit density field from a single image. It maps every location in the frustum of the image to volumetric density. By directly sampling color from the available views instead of storing color in the density field, our scene representation becomes significantly less complex compared to NeRFs, and a neural network can predict it in a single forward pass. The network is trained through self-supervision from only video data. Our formulation allows volume rendering to perform both depth prediction and novel view synthesis. Through experiments, we show that our method is able to predict meaningful geometry for regions that are occluded in the input image. Additionally, we demonstrate the potential of our approach on three datasets for depth prediction and novel-view synthesis.

We consider the problem of predicting the 3D shape, articulation, viewpoint, texture, and lighting of an articulated animal like a horse given a single test image as input. We present a new method, dubbed MagicPony, that learns this predictor purely from in-the-wild single-view images of the object category, with minimal assumptions about the topology of deformation. At its core is an implicit-explicit representation of articulated shape and appearance, combining the strengths of neural fields and meshes. In order to help the model understand an object's shape and pose, we distil the knowledge captured by an off-the-shelf self-supervised vision transformer and fuse it into the 3D model. To overcome local optima in viewpoint estimation, we further introduce a new viewpoint sampling scheme that comes at no additional training cost. MagicPony outperforms prior work on this challenging task and demonstrates excellent generalisation in reconstructing art, despite the fact that it is only trained on real images. The code can be found on the project page at https://3dmagicpony.github.io/

Large-scale Vision-Language Models, such as CLIP, learn powerful image-text representations that have found numerous applications, from zero-shot classification to text-to-image generation. Despite that, their capabilities for solving novel discriminative tasks via prompting fall behind those of large language models, such as GPT-3. Here we explore the idea of visual prompt engineering for solving computer vision tasks beyond classification by editing in image space instead of text. In particular, we discover an emergent ability of CLIP, where, by simply drawing a red circle around an object, we can direct the model’s attention to that region, while also maintaining global information. We show the power of this simple approach by achieving state-of-the-art in zero-shot referring expressions comprehension and strong performance in keypoint localization tasks. Finally, we draw attention to some potential ethical concerns of large language-vision models.

We present Viewset Diffusion, a diffusion-based generator that outputs 3D objects while only using multi-view 2D data for supervision. We note that there exists a one-to-one mapping between viewsets, i.e., collections of several 2D views of an object, and 3D models. Hence, we train a diffusion model to generate viewsets, but design the neural network generator to reconstruct internally corresponding 3D models, thus generating those too. We fit a diffusion model to a large number of viewsets for a given category of objects. The resulting generator can be conditioned on zero, one or more input views. Conditioned on a single view, it performs 3D reconstruction accounting for the ambiguity of the task and allowing to sample multiple solutions compatible with the input. The model performs reconstruction efficiently, in a feed-forward manner, and is trained using only rendering losses using as few as three views per viewset. Project page: szymanowiczs.github.io/viewset-diffusion.

Camera pose estimation is a long-standing computer vision problem that to date often relies on classical methods, such as handcrafted keypoint matching, RANSAC and bundle adjustment. In this paper, we propose to formulate the Structure from Motion (SfM) problem inside a probabilistic diffusion framework, modelling the conditional distribution of camera poses given input images. This novel view of an old problem has several advantages. (i) The nature of the diffusion framework mirrors the iterative procedure of bundle adjustment. (ii) The formulation allows a seamless integration of geometric constraints from epipolar geometry. (iii) It excels in typically difficult scenarios such as sparse views with wide baselines. (iv) The method can predict intrinsics and extrinsics for an arbitrary amount of images. We demonstrate that our method PoseDiffusion significantly improves over the classic SfM pipelines and the learned approaches on two real-world datasets. Finally, it is observed that our method can generalize across datasets without further training. Project page: https://posediffusion.github.io/

Abstract Learning deformable 3D objects from 2D images is often an ill-posed problem. Existing methods rely on explicit supervision to establish multi-view correspondences, such as template shape models and keypoint annotations, which restricts their applicability on objects “in the wild”. A more natural way of establishing correspondences is by watching videos of objects moving around. In this paper, we present DOVE, a method that learns textured 3D models of deformable object categories from monocular videos available online, without keypoint, viewpoint or template shape supervision. By resolving symmetry-induced pose ambiguities and leveraging temporal correspondences in videos, the model automatically learns to factor out 3D shape, articulated pose and texture from each individual RGB frame, and is ready for single-image inference at test time. In the experiments, we show that existing methods fail to learn sensible 3D shapes without additional keypoint or template supervision, whereas our method produces temporally consistent 3D models, which can be animated and rendered from arbitrary viewpoints. Project page: https://dove3d.github.io/ .

We propose a method to learn 3D deformable object categories from raw single-view images, without external supervision. The method is based on an autoencoder that factors each input image into depth, albedo, viewpoint and illumination. In order to disentangle these components without supervision, we use the fact that many object categories have, at least approximately, a symmetric structure. We show that reasoning about illumination allows us to exploit the underlying object symmetry even if the appearance is not symmetric due to shading. Furthermore, we model objects that are probably, but not certainly, symmetric by predicting a symmetry probability map, learned end-to-end with the other components of the model. Our experiments show that this method can recover very accurately the 3D shape of human faces, cat faces and cars from single-view images, without any supervision or a prior shape model. On benchmarks, we demonstrate superior accuracy compared to another method that uses supervision at the level of 2D image correspondences.

Unsupervised localization and segmentation are long-standing computer vision challenges that involve decom-posing an image into semantically meaningful segments without any labeled data. These tasks are particularly interesting in an unsupervised setting due to the difficulty and cost of obtaining dense image annotations, but existing un-supervised approaches struggle with complex scenes containing multiple objects. Differently from existing methods, which are purely based on deep learning, we take inspiration from traditional spectral segmentation methods by re-framing image decomposition as a graph partitioning problem. Specifically, we examine the eigenvectors of the Laplacian of a feature affinity matrix from self-supervised networks. We find that these eigenvectors already decompose an image into meaningful segments, and can be readily used to localize objects in a scene. Furthermore, by clustering the features associated with these segments across a dataset, we can obtain well-delineated, nameable regions, i.e. semantic segmentations. Experiments on complex datasets (PASCAL VOC, MS-COCO) demonstrate that our simple spectral method outperforms the state-of-the-art in unsupervised localization and segmentation by a significant margin. Furthermore, our method can be readily usedfor a variety of complex image editing tasks, such as background removal and compositing.11Project Page: https://lukemelas.github.io/deep-spectral-segmentation/

With increasing focus on augmented and virtual reality (XR) applications comes the demand for algorithms that can lift objects from images into representations that are suitable for a wide variety of related 3D tasks. Large-scale deployment of XR devices and applications means that we cannot solely rely on supervised learning, as collecting and annotating data for the unlimited variety of objects in the real world is infeasible. We present a weakly supervised method that is able to decompose a single image of an object into shape (depth and normals), material (albedo, reflectivity and shininess) and global lighting parameters. For training, the method only relies on a rough initial shape estimate of the training objects to bootstrap the learning process. This shape supervision can come for example from a pretrained depth network or-more generically-from a traditional structure-from-motion pipeline. In our experiments, we show that the method can successfully de-render 2D images into a decomposed 3D representation and generalizes to unseen object categories. Since in-the-wild evaluation is difficult due to the lack of ground truth data, we also introduce a photo-realistic synthetic test set that allows for quantitative evaluation. Please find our project page at: https://github.com/Brummi/derender3d

We propose a new approach to learn to segment multiple image objects without manual supervision. The method can extract objects form still images, but uses videos for supervision. While prior works have considered motion for segmentation, a key insight is that, while motion can be used to identify objects, not all objects are necessarily in motion: the absence of motion does not imply the absence of objects. Hence, our model learns to predict image regions that are likely to contain motion patterns characteristic of objects moving rigidly. It does not predict specific motion, which cannot be done unambiguously from a still image, but a distribution of possible motions, which includes the possibility that an object does not move at all. We demonstrate the advantage of this approach over its deterministic counterpart and show state-of-the-art unsupervised object segmentation performance on simulated and real-world benchmarks, surpassing methods that use motion even at test time. As our approach is applicable to variety of network architectures that segment the scenes, we also apply it to existing image reconstruction-based models showing drastic improvement. Project page and code: https://www.robots.ox.ac.uk/~vgg/research/ppmp.

Is critical input information encoded in specific sparse pathways within the neural network? In this work, we discuss the problem of identifying these critical pathways and subsequently leverage them for interpreting the network’s response to an input. The pruning objective — selecting the smallest group of neurons for which the response remains equivalent to the original network — has been previously proposed for identifying critical pathways. We demonstrate that sparse pathways derived from pruning do not necessarily encode critical input information. To ensure sparse pathways include critical fragments of the encoded input information, we propose pathway selection via neurons’ contribution to the response. We proceed to explain how critical pathways can reveal critical input features. We prove that pathways selected via neuron contribution are locally linear (in an ℓ2-ball), a property that we use for proposing a feature attribution method: "pathway gradient". We validate our interpretation method using mainstream evaluation experiments. The validation of pathway gradient interpretation method further confirms that selected pathways using neuron contributions correspond to critical input features. The code12is publicly available.

We propose a method to learn 3D deformable object categories from raw single-view images, without external supervision. The method is based on an autoencoder that factors each input image into depth, albedo, viewpoint and illumination. In order to disentangle these components without supervision, we use the fact that many object categories have, at least approximately, a symmetric structure. We show that reasoning about illumination allows us to exploit the underlying object symmetry even if the appearance is not symmetric due to shading. Furthermore, we model objects that are probably, but not certainly, symmetric by predicting a symmetry probability map, learned end-to-end with the other components of the model. Our experiments show that this method can recover very accurately the 3D shape of human faces, cat faces and cars from single-view images, without any supervision or a prior shape model. Code and demo available at https://github.com/elliottwu/unsup3d.

The goal of self-supervised visual representation learning is to learn strong, transferable image representations, with the majority of research focusing on object or scene level. On the other hand, representation learning at part level has received significantly less attention. In this paper, we propose an unsupervised approach to object part discovery and segmentation and make three contributions. First, we construct a proxy task through a set of objectives that encourages the model to learn a meaningful decomposition of the image into its parts. Secondly, prior work argues for reconstructing or clustering pre-computed features as a proxy to parts; we show empirically that this alone is unlikely to find meaningful parts; mainly because of their low resolution and the tendency of classification networks to spatially smear out information. We suggest that image reconstruction at the level of pixels can alleviate this problem, acting as a complementary cue. Lastly, we show that the standard evaluation based on keypoint regression does not correlate well with segmentation quality and thus introduce different metrics, NMI and ARI, that better characterize the decomposition of objects into parts. Our method yields semantic parts which are consistent across fine-grained but visually distinct categories, outperforming the state of the art on three benchmark datasets. Code is available at the project page: https://www.robots.ox.ac.uk/~vgg/research/unsup-parts/.

Image manipulation can be considered a special case of image generation where the image to be produced is a modification of an existing image. Image generation and manipulation have been, for the most part, tasks that operate on raw pixels. However, the remarkable progress in learning rich image and object representations has opened the way for tasks such as text-to-image or layout-to-image generation that are mainly driven by semantics. In our work, we address the novel problem of image manipulation from scene graphs, in which a user can edit images by merely applying changes in the nodes or edges of a semantic graph that is generated from the image. Our goal is to encode image information in a given constellation and from there on generate new constellations, such as replacing objects or even changing relationships between objects, while respecting the semantics and style from the original image. We introduce a spatio-semantic scene graph network that does not require direct supervision for constellation changes or image edits. This makes it possible to train the system from existing real-world datasets with no additional annotation effort.

We propose a method to learn 3D deformable object categories from raw single-view images, without external supervision. The method is based on an autoencoder that factors each input image into depth, albedo, viewpoint and illumination. In order to disentangle these components without supervision, we use the fact that many object categories have, at least in principle, a symmetric structure. We show that reasoning about illumination allows us to exploit the underlying object symmetry even if the appearance is not symmetric due to shading. Furthermore, we model objects that are probably, but not certainly, symmetric by predicting a symmetry probability map, learned end-to-end with the other components of the model. Our experiments show that this method can recover very accurately the 3D shape of human faces, cat faces and cars from single-view images, without any supervision or a prior shape model. On benchmarks, we demonstrate superior accuracy compared to another method that uses supervision at the level of 2D image correspondences.

A large part of the current success of deep learning lies in the effectiveness of data -- more precisely: of labeled data. Yet, labelling a dataset with human annotation continues to carry high costs, especially for videos. While in the image domain, recent methods have allowed to generate meaningful (pseudo-) labels for unlabelled datasets without supervision, this development is missing for the video domain where learning feature representations is the current focus. In this work, we a) show that unsupervised labelling of a video dataset does not come for free from strong feature encoders and b) propose a novel clustering method that allows pseudo-labelling of a video dataset without any human annotations, by leveraging the natural correspondence between audio and visual modalities. An extensive analysis shows that the resulting clusters have high semantic overlap to ground truth human labels. We further introduce the first benchmarking results on unsupervised labelling of common video datasets.

Understanding images without explicit supervision has become an important problem in computer vision. In this paper, we address image captioning by generating language descriptions of scenes without learning from annotated pairs of images and their captions. The core component of our approach is a shared latent space that is structured by visual concepts. In this space, the two modalities should be indistinguishable. A language model is first trained to encode sentences into semantically structured embeddings. Image features that are translated into this embedding space can be decoded into descriptions through the same language model, similarly to sentence embeddings. This translation is learned from weakly paired images and text using a loss robust to noisy assignments and a conditional adversarial component. Our approach allows to exploit large text corpora outside the annotated distributions of image/caption data. Our experiments show that the proposed domain alignment learns a semantically meaningful representation which outperforms previous work.

3D object detection and pose estimation from a single image are two inherently ambiguous problems. Oftentimes, objects appear similar from different viewpoints due to shape symmetries, occlusion and repetitive textures. This ambiguity in both detection and pose estimation means that an object instance can be perfectly described by several different poses and even classes. In this work we propose to explicitly deal with these ambiguities. For each object instance we predict multiple 6D pose outcomes to estimate the specific pose distribution generated by symmetries and repetitive textures. The distribution collapses to a single outcome when the visual appearance uniquely identifies just one valid pose. We show the benefits of our approach which provides not only a better explanation for pose ambiguity, but also a higher accuracy in terms of pose estimation.

Interaction and collaboration between humans and intelligent machines has become increasingly important as machine learning methods move into real-world applications that involve end users. While much prior work lies at the intersection of natural language and vision, such as image captioning or image generation from text descriptions, less focus has been placed on the use of language to guide or improve the performance of a learned visual processing algorithm. In this paper, we explore methods to flexibly guide a trained convolutional neural network through user input to improve its performance during inference. We do so by inserting a layer that acts as a spatio-semantic guide into the network. This guide is trained to modify the network's activations, either directly via an energy minimization scheme or indirectly through a recurrent model that translates human language queries to interaction weights. Learning the verbal interaction is fully automatic and does not require manual text annotations. We evaluate the method on two datasets, showing that guiding a pre-trained network can improve performance, and provide extensive insights into the interaction between the guide and the CNN.

Many prediction tasks contain uncertainty. In some cases, uncertainty is inherent in the task itself. In future prediction, for example, many distinct outcomes are equally valid. In other cases, uncertainty arises from the way data is labeled. For example, in object detection, many objects of interest often go unlabeled, and in human pose estimation, occluded joints are often labeled with ambiguous values. In this work we focus on a principled approach for handling such scenarios. In particular, we propose a frame-work for reformulating existing single-prediction models as multiple hypothesis prediction (MHP) models and an associated meta loss and optimization procedure to train them. To demonstrate our approach, we consider four diverse applications: human pose estimation, future prediction, image classification and segmentation. We find that MHP models outperform their single-hypothesis counterparts in all cases, and that MHP models simultaneously expose valuable insights into the variability of predictions.

This paper addresses the problem of estimating the depth map of a scene given a single RGB image. We propose a fully convolutional architecture, encompassing residual learning, to model the ambiguous mapping between monocular images and depth maps. In order to improve the output resolution, we present a novel way to efficiently learn feature map up-sampling within the network. For optimization, we introduce the reverse Huber loss that is particularly suited for the task at hand and driven by the value distributions commonly present in depth maps. Our model is composed of a single architecture that is trained end-to-end and does not rely on post-processing techniques, such as CRFs or other additional refinement steps. As a result, it runs in real-time on images or videos. In the evaluation, we show that the proposed model contains fewer parameters and requires fewer training data than the current state of the art, while outperforming all approaches on depth estimation. Code and models are publicly available.

There are many applications where domain-specific sensing, such as accelerometers, kinematics, or force sensing, provide unique and important information for control or for analysis of motion. However, it is not always the case that these sensors can be deployed or accessed beyond laboratory environments. For example, it is possible to instrument humans or robots to measure motion in the laboratory in ways that it is not possible to replicate in the wild. An alternative, which we explore in this paper, is to address situations where accurate sensing is available while training an algorithm, but for which only video is available for deployment. We present two examples of this sensory substitution methodology. The first variation trains a convolutional neural network to regress real-valued signals, including robot end-effector pose, from video. The second example regresses binary signals derived from accelerometer data which signifies when specific objects are in motion. We evaluate these on the JIGSAWS dataset for robotic surgery training assessment and the 50 Salads dataset for modeling complex structured cooking tasks. We evaluate the trained models for video-based action recognition and show that the trained models provide information that is comparable to the sensory signals they replace.

Consider the following scenario between a human user and the computer. Given an image, the user thinks of an object to be segmented within this picture, but is only allowed to provide binary inputs to the computer (yes or no). In these conditions, can the computer guess this hidden segmentation by asking well-chosen questions to the user? We introduce a strategy for the computer to increase the accuracy of its guess in a minimal number of questions. At each turn, the current belief about the answer is encoded in a Bayesian fashion via a probability distribution over the set of all possible segmentations. To efficiently handle this huge space, the distribution is approximated by sampling representative segmentations using an adapted version of the Metropolis-Hastings algorithm, whose proposal moves build on a geodesic distance transform segmentation method. Following a dichotomic search, the question halving the weighted set of samples is finally picked, and the provided answer is used to update the belief for the upcoming rounds. The performance of this strategy is assessed on three publicly available datasets with diverse visual properties. Our approach shows to be a tractable and very adaptive solution to this problem.

Convolutional Neural Networks (ConvNets) have successfully contributed to improve the accuracy of regression-based methods for computer vision tasks such as human pose estimation, landmark localization, and object detection. The network optimization has been usually performed with L2 loss and without considering the impact of outliers on the training process, where an outlier in this context is defined by a sample estimation that lies at an abnormal distance from the other training sample estimations in the objective space. In this work, we propose a regression model with ConvNets that achieves robustness to such outliers by minimizing Tukey's biweight function, an M-estimator robust to outliers, as the loss function for the ConvNet. In addition to the robust loss, we introduce a coarse-to-fine model, which processes input images of progressively higher resolutions for improving the accuracy of the regressed values. In our experiments, we demonstrate faster convergence and better generalization of our robust loss function for the tasks of human pose estimation and age estimation from face images. We also show that the combination of the robust loss function with the coarse-to-fine model produces comparable or better results than current state-of-the-art approaches in four publicly available human pose estimation datasets.

Statistical human body models, like SCAPE, capture static 3D human body shapes and poses and are applied to many Computer Vision problems. Defined in a statistical context, their parameters do not explicitly capture semantics of the human body shapes such as height, weight, limb length, etc. Having a set of semantic parameters would allow users and automated algorithms to sample the space of possible body shape variations in a more intuitive way. Therefore, in this paper we propose a method for re-parameterization of statistical human body models such that shapes are controlled by a small set of intuitive semantic parameters. These parameters are learned directly from the available statistical human body model. In order to apply any arbitrary animation to our human body shape model we perform retargeting. From any set of 3D scans, a semantic parametrized model can be generated and animated with the presented methods using any animation data. We quantitatively show that our semantic parameterization is more reliable than standard semantic parameterizations, and show a number of animations retargeted to our semantic body shape model.