We propose the Large View Synthesis Model (LVSM), a novel transformer-based approach for scalable and generalizable novel view synthesis from sparse-view inputs. We introduce two architectures: (1) an encoder-decoder LVSM, which encodes input image tokens into a fixed number of 1D latent tokens, functioning as a fully learned scene representation, and decodes novel-view images from them; and (2) a decoder-only LVSM, which directly maps input images to novelview outputs, completely eliminating intermediate scene representations. Both models bypass the 3D inductive biases used in previous methods--from 3D representations (e.g., NeRF, 3DGS) to network designs (e.g., epipolar projections, plane sweeps)--addressing novel view synthesis with a fully data-driven approach. While the encoder-decoder model offers faster inference due to its independent latent representation, the decoder-only LVSM achieves superior quality, scalability, and zero-shot generalization, outperforming previous state-of-the-art methods by 1.5 to 3.5 dB PSNR. Comprehensive evaluations across multiple datasets demonstrate that both LVSM variants achieve state-of-the-art novel view synthesis quality. Notably, our models surpass all previous methods even with reduced computational resources (1-2 GPUs). Novel view synthesis is a long-standing challenge in vision and graphics. For decades, the community has generally relied on various 3D inductive biases, incorporating 3D priors and handcrafted structures to simplify the task and improve synthesis quality. Other methods have also built generalizable networks to estimate these representations or directly generate novel-view images in a feed-forward manner, often incorporating additional 3D inductive biases, such as projective epipolar lines or plane-sweep volumes, in their architecture designs (Wang et al., 2021a; Yu et al., 2021; Chen et al., 2021; Suhail et al., 2022b; Charatan et al., 2024; Chen et al., 2024). While effective, these 3D inductive biases inherently limit model flexibility, constraining their adaptability to more diverse and complex scenarios that do not align with predefined priors or handcrafted structures.

Single-image relighting is a challenging task that involves reasoning about the complex interplay between geometry, materials, and lighting. Many prior methods either support only specific categories of images, such as portraits, or require special capture conditions, like using a flashlight. Alternatively, some methods explicitly decompose a scene into intrinsic components, such as normals and BRDFs, which can be inaccurate or under-expressive. In this work, we propose a novel end-to-end 2D relighting diffusion model, called Neural Gaffer, that takes a single image of any object and can synthesize an accurate, high-quality relit image under any novel environmental lighting condition, simply by conditioning an image generator on a target environment map, without an explicit scene decomposition. Our method builds on a pre-trained diffusion model, and fine-tunes it on a synthetic relighting dataset, revealing and harnessing the inherent understanding of lighting present in the diffusion model. We evaluate our model on both synthetic and in-the-wild Internet imagery and demonstrate its advantages in terms of generalization and accuracy. Moreover, by combining with other generative methods, our model enables many downstream 2D tasks, such as text-based relighting and object insertion. Our model can also operate as a strong relighting prior for 3D tasks, such as relighting a radiance field.

Realistic object interactions are crucial for creating immersive virtual experiences, yet synthesizing realistic 3D object dynamics in response to novel interactions remains a significant challenge. Unlike unconditional or text-conditioned dynamics generation, action-conditioned dynamics requires perceiving the physical material properties of objects and grounding the 3D motion prediction on these properties, such as object stiffness. However, estimating physical material properties is an open problem due to the lack of material ground-truth data, as measuring these properties for real objects is highly difficult. We present Phys-Dreamer, a physics-based approach that endows static 3D objects with interactive dynamics by leveraging the object dynamics priors learned by video generation models. By distilling these priors, PhysDreamer enables the synthesis of realistic object responses to novel interactions, such as external forces or agent manipulations. We demonstrate our approach on diverse examples of elastic objects and evaluate the realism of the synthesized interactions through a user study. PhysDreamer takes a step towards more engaging and realistic virtual experiences by enabling static 3D objects to dynamically respond to interactive stimuli in a physically plausible manner. See our project page at https: //physdreamer.github.io/.

We propose NeRFiller, an approach that completes missing portions of a 3D capture via generative 3D inpainting using off-the-shelf 2D visual generative models. Often parts of a captured 3D scene or object are missing due to mesh reconstruction failures or a lack of observations (e.g., contact regions, such as the bottom of objects, or hard-to-reach areas). We approach this challenging 3D inpainting problem by leveraging a 2D inpainting diffusion model. We identify a surprising behavior of these models, where they generate more 3D consistent inpaints when images form a 2$\times$2 grid, and show how to generalize this behavior to more than four images. We then present an iterative framework to distill these inpainted regions into a single consistent 3D scene. In contrast to related works, we focus on completing scenes rather than deleting foreground objects, and our approach does not require tight 2D object masks or text. We compare our approach to relevant baselines adapted to our setting on a variety of scenes, where NeRFiller creates the most 3D consistent and plausible scene completions. Our project page is at https://ethanweber.me/nerfiller.

The above is also true for an image of a works assume either ground-truth keypoint annotations or "never-before-seen" object (as opposed to a common object a large dataset of images of a single object category. However, category such as cars) where humans demonstrate surprisingly neither of the above assumptions hold true for the longtail robust generalization despite lacking an object or category of the objects present in the world. We present a selfsupervised specific priors [6]. These correspondences in turn inform technique that directly optimizes on a sparse collection downstream inferences about the object such as shape, of images of a particular object/object category to affordances, and more. In this work, we tackle this problem obtain consistent dense correspondences across the collection. of "low-shot dense correspondence" - i.e. given only a small We use pairwise nearest neighbors obtained from deep in-the-wild image collection ( 10-30 images) of an object features of a pre-trained vision transformer (ViT) model as or object category, we recover dense and consistent correspondences noisy and sparse keypoint matches and make them dense across the entire collection.

Despite increasingly realistic image quality, recent 3D image generative models often operate on 3D volumes of fixed extent with limited camera motions. We investigate the task of unconditionally synthesizing unbounded nature scenes, enabling arbitrarily large camera motion while maintaining a persistent 3D world model. Our scene representation consists of an extendable, planar scene layout grid, which can be rendered from arbitrary camera poses via a 3D decoder and volume rendering, and a panoramic skydome. Based on this representation, we learn a generative world model solely from single-view internet photos. Our method enables simulating long flights through 3D landscapes, while maintaining global scene consistency--for instance, returning to the starting point yields the same view of the scene. Our approach enables scene extrapolation beyond the fixed bounds of current 3D generative models, while also supporting a persistent, camera-independent world representation that stands in contrast to auto-regressive 3D prediction models. Our project page: https://chail.github.io/persistent-nature/.

We consider two important aspects in understanding and editing images: modeling regular, program-like texture or patterns in 2D planes, and 3D posing of these planes in the scene. Unlike prior work on image-based program synthesis, which assumes the image contains a single visible 2D plane, we present Box Program Induction (BPI), which infers a program-like scene representation that simultaneously models repeated structure on multiple 2D planes, the 3D position and orientation of the planes, and camera parameters, all from a single image. Our model assumes a box prior, i.e., that the image captures either an inner view or an outer view of a box in 3D. It uses neural networks to infer visual cues such as vanishing points or wireframe lines to guide a search-based algorithm to find the program that best explains the image. Such a holistic, structured scene representation enables 3D-aware interactive image editing operations such as inpainting missing pixels, changing camera parameters, and extrapolate the image contents.

This paper presents KeypointNet, an end-to-end geometric reasoning framework to learn an optimal set of category-specific 3D keypoints, along with their detectors. Given a single image, KeypointNet extracts 3D keypoints that are optimized for a downstream task. We demonstrate this framework on 3D pose estimation by proposing a differentiable objective that seeks the optimal set of keypoints for recovering the relative pose between two views of an object. Our model discovers geometrically and semantically consistent keypoints across viewing angles and instances of an object category. Importantly, we find that our end-to-end framework using no ground-truth keypoint annotations outperforms a fully supervised baseline using the same neural network architecture on the task of pose estimation. The discovered 3D keypoints on the car, chair, and plane categories of ShapeNet [6] are visualized at keypointnet.github.io.

This paper presents KeypointNet, an end-to-end geometric reasoning framework to learn an optimal set of category-specific 3D keypoints, along with their detectors. Given a single image, KeypointNet extracts 3D keypoints that are optimized for a downstream task. We demonstrate this framework on 3D pose estimation by proposing a differentiable objective that seeks the optimal set of keypoints for recovering the relative pose between two views of an object. Our model discovers geometrically and semantically consistent keypoints across viewing angles and instances of an object category. Importantly, we find that our end-to-end framework using no ground-truth keypoint annotations outperforms a fully supervised baseline using the same neural network architecture on the task of pose estimation. The discovered 3D keypoints on the car, chair, and plane categories of ShapeNet [6] are visualized at keypointnet.github.io.

We study the problem of jointly reasoning about language and vision through a navigation and spatial reasoning task. We introduce the Touchdown task and dataset, where an agent must first follow navigation instructions in a real-life visual urban environment to a goal position, and then identify in the observed image a location described in natural language to find a hidden object. The data contains 9,326 examples of English instructions and spatial descriptions paired with demonstrations. We perform qualitative linguistic analysis, and show that the data displays richer use of spatial reasoning compared to related resources. Empirical analysis shows the data presents an open challenge to existing methods.