Rundi Wu

Ruoshi Liu, Rundi Wu, Basile Van Hoorick et al.

We introduce Zero-1-to-3, a framework for changing the camera viewpoint of an object given just a single RGB image. To perform novel view synthesis in this under-constrained setting, we capitalize on the geometric priors that large-scale diffusion models learn about natural images. Our conditional diffusion model uses a synthetic dataset to learn controls of the relative camera viewpoint, which allow new images to be generated of the same object under a specified camera transformation. Even though it is trained on a synthetic dataset, our model retains a strong zero-shot generalization ability to out-of-distribution datasets as well as in-the-wild images, including impressionist paintings. Our viewpoint-conditioned diffusion approach can further be used for the task of 3D reconstruction from a single image. Qualitative and quantitative experiments show that our method significantly outperforms state-of-the-art single-view 3D reconstruction and novel view synthesis models by leveraging Internet-scale pre-training.

Honglin Chen, Rundi Wu, Eitan Grinspun et al.

Implicit Neural Spatial Representation (INSR) has emerged as an effective representation of spatially-dependent vector fields. This work explores solving time-dependent PDEs with INSR. Classical PDE solvers introduce both temporal and spatial discretizations. Common spatial discretizations include meshes and meshless point clouds, where each degree-of-freedom corresponds to a location in space. While these explicit spatial correspondences are intuitive to model and understand, these representations are not necessarily optimal for accuracy, memory usage, or adaptivity. Keeping the classical temporal discretization unchanged (e.g., explicit/implicit Euler), we explore INSR as an alternative spatial discretization, where spatial information is implicitly stored in the neural network weights. The network weights then evolve over time via time integration. Our approach does not require any training data generated by existing solvers because our approach is the solver itself. We validate our approach on various PDEs with examples involving large elastic deformations, turbulent fluids, and multi-scale phenomena. While slower to compute than traditional representations, our approach exhibits higher accuracy and lower memory consumption. Whereas classical solvers can dynamically adapt their spatial representation only by resorting to complex remeshing algorithms, our INSR approach is intrinsically adaptive. By tapping into the rich literature of classic time integrators, e.g., operator-splitting schemes, our method enables challenging simulations in contact mechanics and turbulent flows where previous neural-physics approaches struggle. Videos and codes are available on the project page: http://www.cs.columbia.edu/cg/INSR-PDE/

Yufan Zhang, Yu Ji, Ayo Ajiboye et al.

We present a diffusion-based method for relighting dynamic portrait videos with photorealism and temporal consistency. Our method is fueled by a hybrid training dataset that consists of real-captured and rendered dynamic portrait videos with diverse subject appearances, facial motions, head poses, and known lighting conditions. Specifically, we construct an LED-based lighting system for realistic lighting emulation and high-speed video relighting data acquisition. By leveraging the image priors embedded in pre-trained video diffusion models, and using per-frame high dynamic range (HDR) environment map as lighting control, we train a high-performance generative model for realistic and identity-preserving dynamic portrait video relighting. In addition to the environment map control, our model uses a synthesized background image to enable control on the camera's exposure level and color tone. Our model can produce temporally consistent relit portrait video that looks realistic and harmonious under a provided new environment and faithfully preserve the subject's expression and fine facial features, including skin tone, wrinkles, and facial hair. Our model generalizes well to unseen data, in terms of the subject appearance, motion, and lighting condition. We perform extensive experiments on relighting in-the-wild videos with various environment maps and demonstrate practical applications on portrait photography. Results show that our method achieves state-of-the-art performance in photorealism, lighting harmony, and temporal consistency.

Rundi Wu, Changxi Zheng

Existing generative models for 3D shapes are typically trained on a large 3D dataset, often of a specific object category. In this paper, we investigate the deep generative model that learns from only a single reference 3D shape. Specifically, we present a multi-scale GAN-based model designed to capture the input shape's geometric features across a range of spatial scales. To avoid large memory and computational cost induced by operating on the 3D volume, we build our generator atop the tri-plane hybrid representation, which requires only 2D convolutions. We train our generative model on a voxel pyramid of the reference shape, without the need of any external supervision or manual annotation. Once trained, our model can generate diverse and high-quality 3D shapes possibly of different sizes and aspect ratios. The resulting shapes present variations across different scales, and at the same time retain the global structure of the reference shape. Through extensive evaluation, both qualitative and quantitative, we demonstrate that our model can generate 3D shapes of various types.

Honglin Chen, Karran Pandey, Rundi Wu et al.

Kinematic rigs provide a structured interface for articulating 3D meshes, but they lack an inherent representation of the plausible manifold of joint configurations for a given asset. Without such a pose space, stochastic sampling or manual manipulation of raw rig parameters often leads to semantic or geometric violations, such as anatomical hyperextension and non-physical self-intersections. We propose Video-informed Pose Spaces (ViPS), a feed-forward framework that discovers the latent distribution of valid articulations for auto-rigged meshes by distilling motion priors from a pretrained video diffusion model. Unlike existing methods that rely on scarce artist-authored 4D datasets, ViPS transfers generative video priors into a universal distribution over a given rig parameterization. Differentiable geometric validators applied to the skinned mesh enforce asset-specific validity without requiring manual regularizers. Our model learns a smooth, compact, and controllable pose space that supports diverse sampling, manifold projection for inverse kinematics, and temporally coherent trajectories for keyframing. Furthermore, the distilled 3D pose samples serve as precise semantic proxies for guiding video diffusion, effectively closing the loop between generative 2D priors and structured 3D kinematic control. Our evaluations show that ViPS, trained solely on video priors, matches the performance of state-of-the-art methods trained on synthetic artist-created 4D data in both plausibility and diversity. Most importantly, as a universal model, ViPS demonstrates robust zero-shot generalization to out-of-distribution species and unseen skeletal topologies.

Haian Jin, Rundi Wu, Tianyuan Zhang et al.

Feed-forward transformer models have driven rapid progress in 3D vision, but state-of-the-art methods such as VGGT and $π^3$ have a computational cost that scales quadratically with the number of input images, making them inefficient when applied to large image collections. Sequential-reconstruction approaches reduce this cost but sacrifice reconstruction quality. We introduce ZipMap, a stateful feed-forward model that achieves linear-time, bidirectional 3D reconstruction while matching or surpassing the accuracy of quadratic-time methods. ZipMap employs test-time training layers to zip an entire image collection into a compact hidden scene state in a single forward pass, enabling reconstruction of over 700 frames in under 10 seconds on a single H100 GPU, more than $20\times$ faster than state-of-the-art methods such as VGGT. Moreover, we demonstrate the benefits of having a stateful representation in real-time scene-state querying and its extension to sequential streaming reconstruction.

Beichen Li, Rundi Wu, Armando Solar-Lezama et al.

Procedural materials, represented as functional node graphs, are ubiquitous in computer graphics for photorealistic material appearance design. They allow users to perform intuitive and precise editing to achieve desired visual appearances. However, creating a procedural material given an input image requires professional knowledge and significant effort. In this work, we leverage the ability to convert procedural materials into standard Python programs and fine-tune a large pre-trained vision-language model (VLM) to generate such programs from input images. To enable effective fine-tuning, we also contribute an open-source procedural material dataset and propose to perform program-level augmentation by prompting another pre-trained large language model (LLM). Through extensive evaluation, we show that our method outperforms previous methods on both synthetic and real-world examples.

Rundi Wu, Ben Mildenhall, Philipp Henzler et al.

3D reconstruction methods such as Neural Radiance Fields (NeRFs) excel at rendering photorealistic novel views of complex scenes. However, recovering a high-quality NeRF typically requires tens to hundreds of input images, resulting in a time-consuming capture process. We present ReconFusion to reconstruct real-world scenes using only a few photos. Our approach leverages a diffusion prior for novel view synthesis, trained on synthetic and multiview datasets, which regularizes a NeRF-based 3D reconstruction pipeline at novel camera poses beyond those captured by the set of input images. Our method synthesizes realistic geometry and texture in underconstrained regions while preserving the appearance of observed regions. We perform an extensive evaluation across various real-world datasets, including forward-facing and 360-degree scenes, demonstrating significant performance improvements over previous few-view NeRF reconstruction approaches.

Tianyuan Zhang, Hong-Xing Yu, Rundi Wu et al. · deepmind, stanford

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 PhysDreamer, 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/.

Rundi Wu, Ruiqi Gao, Ben Poole et al.

We present CAT4D, a method for creating 4D (dynamic 3D) scenes from monocular video. CAT4D leverages a multi-view video diffusion model trained on a diverse combination of datasets to enable novel view synthesis at any specified camera poses and timestamps. Combined with a novel sampling approach, this model can transform a single monocular video into a multi-view video, enabling robust 4D reconstruction via optimization of a deformable 3D Gaussian representation. We demonstrate competitive performance on novel view synthesis and dynamic scene reconstruction benchmarks, and highlight the creative capabilities for 4D scene generation from real or generated videos. See our project page for results and interactive demos: https://cat-4d.github.io/.

Basile Van Hoorick, Rundi Wu, Ege Ozguroglu et al.

Accurate reconstruction of complex dynamic scenes from just a single viewpoint continues to be a challenging task in computer vision. Current dynamic novel view synthesis methods typically require videos from many different camera viewpoints, necessitating careful recording setups, and significantly restricting their utility in the wild as well as in terms of embodied AI applications. In this paper, we propose $\textbf{GCD}$, a controllable monocular dynamic view synthesis pipeline that leverages large-scale diffusion priors to, given a video of any scene, generate a synchronous video from any other chosen perspective, conditioned on a set of relative camera pose parameters. Our model does not require depth as input, and does not explicitly model 3D scene geometry, instead performing end-to-end video-to-video translation in order to achieve its goal efficiently. Despite being trained on synthetic multi-view video data only, zero-shot real-world generalization experiments show promising results in multiple domains, including robotics, object permanence, and driving environments. We believe our framework can potentially unlock powerful applications in rich dynamic scene understanding, perception for robotics, and interactive 3D video viewing experiences for virtual reality.

Alex Trevithick, Roni Paiss, Philipp Henzler et al.

Novel-view synthesis techniques achieve impressive results for static scenes but struggle when faced with the inconsistencies inherent to casual capture settings: varying illumination, scene motion, and other unintended effects that are difficult to model explicitly. We present an approach for leveraging generative video models to simulate the inconsistencies in the world that can occur during capture. We use this process, along with existing multi-view datasets, to create synthetic data for training a multi-view harmonization network that is able to reconcile inconsistent observations into a consistent 3D scene. We demonstrate that our world-simulation strategy significantly outperforms traditional augmentation methods in handling real-world scene variations, thereby enabling highly accurate static 3D reconstructions in the presence of a variety of challenging inconsistencies. Project page: https://alextrevithick.github.io/simvs

Mutian Tong, Rundi Wu, Changxi Zheng

Indoor lighting estimation from a single image or video remains a challenge due to its highly ill-posed nature, especially when the lighting condition of the scene varies spatially and temporally. We propose a method that estimates from an input video a continuous light field describing the spatiotemporally varying lighting of the scene. We leverage 2D diffusion priors for optimizing such light field represented as a MLP. To enable zero-shot generalization to in-the-wild scenes, we fine-tune a pre-trained image diffusion model to predict lighting at multiple locations by jointly inpainting multiple chrome balls as light probes. We evaluate our method on indoor lighting estimation from a single image or video and show superior performance over compared baselines. Most importantly, we highlight results on spatiotemporally consistent lighting estimation from in-the-wild videos, which is rarely demonstrated in previous works.

Rundi Wu, Ruoshi Liu, Carl Vondrick et al.

Synthesizing novel 3D models that resemble the input example has long been pursued by graphics artists and machine learning researchers. In this paper, we present Sin3DM, a diffusion model that learns the internal patch distribution from a single 3D textured shape and generates high-quality variations with fine geometry and texture details. Training a diffusion model directly in 3D would induce large memory and computational cost. Therefore, we first compress the input into a lower-dimensional latent space and then train a diffusion model on it. Specifically, we encode the input 3D textured shape into triplane feature maps that represent the signed distance and texture fields of the input. The denoising network of our diffusion model has a limited receptive field to avoid overfitting, and uses triplane-aware 2D convolution blocks to improve the result quality. Aside from randomly generating new samples, our model also facilitates applications such as retargeting, outpainting and local editing. Through extensive qualitative and quantitative evaluation, we show that our method outperforms prior methods in generation quality of 3D shapes.

Rundi Wu, Chang Xiao, Changxi Zheng

Deep generative models of 3D shapes have received a great deal of research interest. Yet, almost all of them generate discrete shape representations, such as voxels, point clouds, and polygon meshes. We present the first 3D generative model for a drastically different shape representation --- describing a shape as a sequence of computer-aided design (CAD) operations. Unlike meshes and point clouds, CAD models encode the user creation process of 3D shapes, widely used in numerous industrial and engineering design tasks. However, the sequential and irregular structure of CAD operations poses significant challenges for existing 3D generative models. Drawing an analogy between CAD operations and natural language, we propose a CAD generative network based on the Transformer. We demonstrate the performance of our model for both shape autoencoding and random shape generation. To train our network, we create a new CAD dataset consisting of 178,238 models and their CAD construction sequences. We have made this dataset publicly available to promote future research on this topic.

Ruilin Xu, Rundi Wu, Yuko Ishiwaka et al.

We introduce a deep learning model for speech denoising, a long-standing challenge in audio analysis arising in numerous applications. Our approach is based on a key observation about human speech: there is often a short pause between each sentence or word. In a recorded speech signal, those pauses introduce a series of time periods during which only noise is present. We leverage these incidental silent intervals to learn a model for automatic speech denoising given only mono-channel audio. Detected silent intervals over time expose not just pure noise but its time-varying features, allowing the model to learn noise dynamics and suppress it from the speech signal. Experiments on multiple datasets confirm the pivotal role of silent interval detection for speech denoising, and our method outperforms several state-of-the-art denoising methods, including those that accept only audio input (like ours) and those that denoise based on audiovisual input (and hence require more information). We also show that our method enjoys excellent generalization properties, such as denoising spoken languages not seen during training.

Rundi Wu, Xuelin Chen, Yixin Zhuang et al.

Several deep learning methods have been proposed for completing partial data from shape acquisition setups, i.e., filling the regions that were missing in the shape. These methods, however, only complete the partial shape with a single output, ignoring the ambiguity when reasoning the missing geometry. Hence, we pose a multi-modal shape completion problem, in which we seek to complete the partial shape with multiple outputs by learning a one-to-many mapping. We develop the first multimodal shape completion method that completes the partial shape via conditional generative modeling, without requiring paired training data. Our approach distills the ambiguity by conditioning the completion on a learned multimodal distribution of possible results. We extensively evaluate the approach on several datasets that contain varying forms of shape incompleteness, and compare among several baseline methods and variants of our methods qualitatively and quantitatively, demonstrating the merit of our method in completing partial shapes with both diversity and quality.

Rundi Wu, Yixin Zhuang, Kai Xu et al.

We introduce PQ-NET, a deep neural network which represents and generates 3D shapes via sequential part assembly. The input to our network is a 3D shape segmented into parts, where each part is first encoded into a feature representation using a part autoencoder. The core component of PQ-NET is a sequence-to-sequence or Seq2Seq autoencoder which encodes a sequence of part features into a latent vector of fixed size, and the decoder reconstructs the 3D shape, one part at a time, resulting in a sequential assembly. The latent space formed by the Seq2Seq encoder encodes both part structure and fine part geometry. The decoder can be adapted to perform several generative tasks including shape autoencoding, interpolation, novel shape generation, and single-view 3D reconstruction, where the generated shapes are all composed of meaningful parts.

Kfir Aberman, Rundi Wu, Dani Lischinski et al.

Analyzing human motion is a challenging task with a wide variety of applications in computer vision and in graphics. One such application, of particular importance in computer animation, is the retargeting of motion from one performer to another. While humans move in three dimensions, the vast majority of human motions are captured using video, requiring 2D-to-3D pose and camera recovery, before existing retargeting approaches may be applied. In this paper, we present a new method for retargeting video-captured motion between different human performers, without the need to explicitly reconstruct 3D poses and/or camera parameters. In order to achieve our goal, we learn to extract, directly from a video, a high-level latent motion representation, which is invariant to the skeleton geometry and the camera view. Our key idea is to train a deep neural network to decompose temporal sequences of 2D poses into three components: motion, skeleton, and camera view-angle. Having extracted such a representation, we are able to re-combine motion with novel skeletons and camera views, and decode a retargeted temporal sequence, which we compare to a ground truth from a synthetic dataset. We demonstrate that our framework can be used to robustly extract human motion from videos, bypassing 3D reconstruction, and outperforming existing retargeting methods, when applied to videos in-the-wild. It also enables additional applications, such as performance cloning, video-driven cartoons, and motion retrieval.