Niloy J. Mitra

Niladri Shekhar Dutt, Sanjeev Muralikrishnan, Niloy J. Mitra

We present Diff3F as a simple, robust, and class-agnostic feature descriptor that can be computed for untextured input shapes (meshes or point clouds). Our method distills diffusion features from image foundational models onto input shapes. Specifically, we use the input shapes to produce depth and normal maps as guidance for conditional image synthesis. In the process, we produce (diffusion) features in 2D that we subsequently lift and aggregate on the original surface. Our key observation is that even if the conditional image generations obtained from multi-view rendering of the input shapes are inconsistent, the associated image features are robust and, hence, can be directly aggregated across views. This produces semantic features on the input shapes, without requiring additional data or training. We perform extensive experiments on multiple benchmarks (SHREC'19, SHREC'20, FAUST, and TOSCA) and demonstrate that our features, being semantic instead of geometric, produce reliable correspondence across both isometric and non-isometrically related shape families. Code is available via the project page at https://diff3f.github.io/

Rishabh Kabra, Loic Matthey, Alexander Lerchner et al. · deepmind

Pretrained vision language models (VLMs) present an opportunity to caption unlabeled 3D objects at scale. The leading approach to summarize VLM descriptions from different views of an object (Luo et al., 2023) relies on a language model (GPT4) to produce the final output. This text-based aggregation is susceptible to hallucinations as it merges potentially contradictory descriptions. We propose an alternative algorithm to marginalize over factors such as the viewpoint that affect the VLM's response. Instead of merging text-only responses, we utilize the VLM's joint image-text likelihoods. We show our probabilistic aggregation is not only more reliable and efficient, but sets the SoTA on inferring object types with respect to human-verified labels. The aggregated annotations are also useful for conditional inference; they improve downstream predictions (e.g., of object material) when the object's type is specified as an auxiliary text-based input. Such auxiliary inputs allow ablating the contribution of visual reasoning over visionless reasoning in an unsupervised setting. With these supervised and unsupervised evaluations, we show how a VLM-based pipeline can be leveraged to produce reliable annotations for 764K objects from the Objaverse dataset.

Duygu Ceylan, Chun-Hao Paul Huang, Niloy J. Mitra

Image diffusion models, trained on massive image collections, have emerged as the most versatile image generator model in terms of quality and diversity. They support inverting real images and conditional (e.g., text) generation, making them attractive for high-quality image editing applications. We investigate how to use such pre-trained image models for text-guided video editing. The critical challenge is to achieve the target edits while still preserving the content of the source video. Our method works in two simple steps: first, we use a pre-trained structure-guided (e.g., depth) image diffusion model to perform text-guided edits on an anchor frame; then, in the key step, we progressively propagate the changes to the future frames via self-attention feature injection to adapt the core denoising step of the diffusion model. We then consolidate the changes by adjusting the latent code for the frame before continuing the process. Our approach is training-free and generalizes to a wide range of edits. We demonstrate the effectiveness of the approach by extensive experimentation and compare it against four different prior and parallel efforts (on ArXiv). We demonstrate that realistic text-guided video edits are possible, without any compute-intensive preprocessing or video-specific finetuning.

Animesh Karnewar, Andrea Vedaldi, David Novotny et al.

Diffusion models have emerged as the best approach for generative modeling of 2D images. Part of their success is due to the possibility of training them on millions if not billions of images with a stable learning objective. However, extending these models to 3D remains difficult for two reasons. First, finding a large quantity of 3D training data is much more complex than for 2D images. Second, while it is conceptually trivial to extend the models to operate on 3D rather than 2D grids, the associated cubic growth in memory and compute complexity makes this infeasible. We address the first challenge by introducing a new diffusion setup that can be trained, end-to-end, with only posed 2D images for supervision; and the second challenge by proposing an image formation model that decouples model memory from spatial memory. We evaluate our method on real-world data, using the CO3D dataset which has not been used to train 3D generative models before. We show that our diffusion models are scalable, train robustly, and are competitive in terms of sample quality and fidelity to existing approaches for 3D generative modeling.

Titas Anciukevičius, Zexiang Xu, Matthew Fisher et al.

Diffusion models currently achieve state-of-the-art performance for both conditional and unconditional image generation. However, so far, image diffusion models do not support tasks required for 3D understanding, such as view-consistent 3D generation or single-view object reconstruction. In this paper, we present RenderDiffusion, the first diffusion model for 3D generation and inference, trained using only monocular 2D supervision. Central to our method is a novel image denoising architecture that generates and renders an intermediate three-dimensional representation of a scene in each denoising step. This enforces a strong inductive structure within the diffusion process, providing a 3D consistent representation while only requiring 2D supervision. The resulting 3D representation can be rendered from any view. We evaluate RenderDiffusion on FFHQ, AFHQ, ShapeNet and CLEVR datasets, showing competitive performance for generation of 3D scenes and inference of 3D scenes from 2D images. Additionally, our diffusion-based approach allows us to use 2D inpainting to edit 3D scenes.

Animesh Karnewar, Tobias Ritschel, Oliver Wang et al.

In many recent works, multi-layer perceptions (MLPs) have been shown to be suitable for modeling complex spatially-varying functions including images and 3D scenes. Although the MLPs are able to represent complex scenes with unprecedented quality and memory footprint, this expressive power of the MLPs, however, comes at the cost of long training and inference times. On the other hand, bilinear/trilinear interpolation on regular grid based representations can give fast training and inference times, but cannot match the quality of MLPs without requiring significant additional memory. Hence, in this work, we investigate what is the smallest change to grid-based representations that allows for retaining the high fidelity result of MLPs while enabling fast reconstruction and rendering times. We introduce a surprisingly simple change that achieves this task -- simply allowing a fixed non-linearity (ReLU) on interpolated grid values. When combined with coarse to-fine optimization, we show that such an approach becomes competitive with the state-of-the-art. We report results on radiance fields, and occupancy fields, and compare against multiple existing alternatives. Code and data for the paper are available at https://geometry.cs.ucl.ac.uk/projects/2022/relu_fields.

Animesh Karnewar, Niloy J. Mitra, Andrea Vedaldi et al.

Diffusion-based image generators can now produce high-quality and diverse samples, but their success has yet to fully translate to 3D generation: existing diffusion methods can either generate low-resolution but 3D consistent outputs, or detailed 2D views of 3D objects but with potential structural defects and lacking view consistency or realism. We present HoloFusion, a method that combines the best of these approaches to produce high-fidelity, plausible, and diverse 3D samples while learning from a collection of multi-view 2D images only. The method first generates coarse 3D samples using a variant of the recently proposed HoloDiffusion generator. Then, it independently renders and upsamples a large number of views of the coarse 3D model, super-resolves them to add detail, and distills those into a single, high-fidelity implicit 3D representation, which also ensures view consistency of the final renders. The super-resolution network is trained as an integral part of HoloFusion, end-to-end, and the final distillation uses a new sampling scheme to capture the space of super-resolved signals. We compare our method against existing baselines, including DreamFusion, Get3D, EG3D, and HoloDiffusion, and achieve, to the best of our knowledge, the most realistic results on the challenging CO3Dv2 dataset.

Anna Frühstück, Krishna Kumar Singh, Eli Shechtman et al.

While GANs can produce photo-realistic images in ideal conditions for certain domains, the generation of full-body human images remains difficult due to the diversity of identities, hairstyles, clothing, and the variance in pose. Instead of modeling this complex domain with a single GAN, we propose a novel method to combine multiple pretrained GANs, where one GAN generates a global canvas (e.g., human body) and a set of specialized GANs, or insets, focus on different parts (e.g., faces, shoes) that can be seamlessly inserted onto the global canvas. We model the problem as jointly exploring the respective latent spaces such that the generated images can be combined, by inserting the parts from the specialized generators onto the global canvas, without introducing seams. We demonstrate the setup by combining a full body GAN with a dedicated high-quality face GAN to produce plausible-looking humans. We evaluate our results with quantitative metrics and user studies.

Meng Zhang, Duygu Ceylan, Niloy J. Mitra

Realistic dynamic garments on animated characters have many AR/VR applications. While authoring such dynamic garment geometry is still a challenging task, data-driven simulation provides an attractive alternative, especially if it can be controlled simply using the motion of the underlying character. In this work, we focus on motion guided dynamic 3D garments, especially for loose garments. In a data-driven setup, we first learn a generative space of plausible garment geometries. Then, we learn a mapping to this space to capture the motion dependent dynamic deformations, conditioned on the previous state of the garment as well as its relative position with respect to the underlying body. Technically, we model garment dynamics, driven using the input character motion, by predicting per-frame local displacements in a canonical state of the garment that is enriched with frame-dependent skinning weights to bring the garment to the global space. We resolve any remaining per-frame collisions by predicting residual local displacements. The resultant garment geometry is used as history to enable iterative rollout prediction. We demonstrate plausible generalization to unseen body shapes and motion inputs, and show improvements over multiple state-of-the-art alternatives.

Connor Z. Lin, Niloy J. Mitra, Gordon Wetzstein et al.

Neural representations are popular for representing shapes, as they can be learned form sensor data and used for data cleanup, model completion, shape editing, and shape synthesis. Current neural representations can be categorized as either overfitting to a single object instance, or representing a collection of objects. However, neither allows accurate editing of neural scene representations: on the one hand, methods that overfit objects achieve highly accurate reconstructions, but do not generalize to unseen object configurations and thus cannot support editing; on the other hand, methods that represent a family of objects with variations do generalize but produce only approximate reconstructions. We propose NEUFORM to combine the advantages of both overfitted and generalizable representations by adaptively using the one most appropriate for each shape region: the overfitted representation where reliable data is available, and the generalizable representation everywhere else. We achieve this with a carefully designed architecture and an approach that blends the network weights of the two representations, avoiding seams and other artifacts. We demonstrate edits that successfully reconfigure parts of human-designed shapes, such as chairs, tables, and lamps, while preserving semantic integrity and the accuracy of an overfitted shape representation. We compare with two state-of-the-art competitors and demonstrate clear improvements in terms of plausibility and fidelity of the resultant edits.

Hugo Bertiche, Niloy J. Mitra, Kuldeep Kulkarni et al.

Cinemagraphs are short looping videos created by adding subtle motions to a static image. This kind of media is popular and engaging. However, automatic generation of cinemagraphs is an underexplored area and current solutions require tedious low-level manual authoring by artists. In this paper, we present an automatic method that allows generating human cinemagraphs from single RGB images. We investigate the problem in the context of dressed humans under the wind. At the core of our method is a novel cyclic neural network that produces looping cinemagraphs for the target loop duration. To circumvent the problem of collecting real data, we demonstrate that it is possible, by working in the image normal space, to learn garment motion dynamics on synthetic data and generalize to real data. We evaluate our method on both synthetic and real data and demonstrate that it is possible to create compelling and plausible cinemagraphs from single RGB images.

Wamiq Reyaz Para, Paul Guerrero, Niloy Mitra et al.

Scalable generation of furniture layouts is essential for many applications in virtual reality, augmented reality, game development and synthetic data generation. Many existing methods tackle this problem as a sequence generation problem which imposes a specific ordering on the elements of the layout making such methods impractical for interactive editing or scene completion. Additionally, most methods focus on generating layouts unconditionally and offer minimal control over the generated layouts. We propose COFS, an architecture based on standard transformer architecture blocks from language modeling. The proposed model is invariant to object order by design, removing the unnatural requirement of specifying an object generation order. Furthermore, the model allows for user interaction at multiple levels enabling fine grained control over the generation process. Our model consistently outperforms other methods which we verify by performing quantitative evaluations. Our method is also faster to train and sample from, compared to existing methods.

Binglun Wang, Niladri Shekhar Dutt, Niloy J. Mitra

Neural Radiance Fields (NeRFs) have recently emerged as a popular option for photo-realistic object capture due to their ability to faithfully capture high-fidelity volumetric content even from handheld video input. Although much research has been devoted to efficient optimization leading to real-time training and rendering, options for interactive editing NeRFs remain limited. We present a very simple but effective neural network architecture that is fast and efficient while maintaining a low memory footprint. This architecture can be incrementally guided through user-friendly image-based edits. Our representation allows straightforward object selection via semantic feature distillation at the training stage. More importantly, we propose a local 3D-aware image context to facilitate view-consistent image editing that can then be distilled into fine-tuned NeRFs, via geometric and appearance adjustments. We evaluate our setup on a variety of examples to demonstrate appearance and geometric edits and report 10-30x speedup over concurrent work focusing on text-guided NeRF editing. Video results can be seen on our project webpage at https://proteusnerf.github.io.

Luca Morreale, Noam Aigerman, Paul Guerrero et al.

This work is concerned with a representation of shapes that disentangles fine, local and possibly repeating geometry, from global, coarse structures. Achieving such disentanglement leads to two unrelated advantages: i) a significant compression in the number of parameters required to represent a given geometry; ii) the ability to manipulate either global geometry, or local details, without harming the other. At the core of our approach lies a novel pipeline and neural architecture, which are optimized to represent one specific atlas, representing one 3D surface. Our pipeline and architecture are designed so that disentanglement of global geometry from local details is accomplished through optimization, in a completely unsupervised manner. We show that this approach achieves better neural shape compression than the state of the art, as well as enabling manipulation and transfer of shape details. Project page at http://geometry.cs.ucl.ac.uk/projects/2022/cnnmaps/ .

Animesh Karnewar, Oliver Wang, Tobias Ritschel et al.

We introduce 3inGAN, an unconditional 3D generative model trained from 2D images of a single self-similar 3D scene. Such a model can be used to produce 3D "remixes" of a given scene, by mapping spatial latent codes into a 3D volumetric representation, which can subsequently be rendered from arbitrary views using physically based volume rendering. By construction, the generated scenes remain view-consistent across arbitrary camera configurations, without any flickering or spatio-temporal artifacts. During training, we employ a combination of 2D, obtained through differentiable volume tracing, and 3D Generative Adversarial Network (GAN) losses, across multiple scales, enforcing realism on both its 3D structure and the 2D renderings. We show results on semi-stochastic scenes of varying scale and complexity, obtained from real and synthetic sources. We demonstrate, for the first time, the feasibility of learning plausible view-consistent 3D scene variations from a single exemplar scene and provide qualitative and quantitative comparisons against recent related methods.

Romy Williamson, Niloy J. Mitra

Neural surfaces (e.g., neural map encoding, deep implicits and neural radiance fields) have recently gained popularity because of their generic structure (e.g., multi-layer perceptron) and easy integration with modern learning-based setups. Traditionally, we have a rich toolbox of geometry processing algorithms designed for polygonal meshes to analyze and operate on surface geometry. In the absence of an analogous toolbox, neural representations are typically discretized and converted into a mesh, before applying any geometry processing algorithm. This is unsatisfactory and, as we demonstrate, unnecessary. In this work, we propose a spherical neural surface representation for genus-0 surfaces and demonstrate how to compute core geometric operators directly on this representation. Namely, we estimate surface normals and first and second fundamental forms of the surface, as well as compute surface gradient, surface divergence and Laplace-Beltrami operator on scalar/vector fields defined on the surface. Our representation is fully seamless, overcoming a key limitation of similar explicit representations such as Neural Surface Maps [Morreale et al. 2021]. These operators, in turn, enable geometry processing directly on the neural representations without any unnecessary meshing. We demonstrate illustrative applications in (neural) spectral analysis, heat flow and mean curvature flow, and evaluate robustness to isometric shape variations. We propose theoretical formulations and validate their numerical estimates, against analytical estimates, mesh-based baselines, and neural alternatives, where available. By systematically linking neural surface representations with classical geometry processing algorithms, we believe that this work can become a key ingredient in enabling neural geometry processing. Code is accessible from the project webpage.

Luca Morreale, Noam Aigerman, Vladimir G. Kim et al.

We present an automated technique for computing a map between two genus-zero shapes, which matches semantically corresponding regions to one another. Lack of annotated data prohibits direct inference of 3D semantic priors; instead, current State-of-the-art methods predominantly optimize geometric properties or require varying amounts of manual annotation. To overcome the lack of annotated training data, we distill semantic matches from pre-trained vision models: our method renders the pair of 3D shapes from multiple viewpoints; the resulting renders are then fed into an off-the-shelf image-matching method which leverages a pretrained visual model to produce feature points. This yields semantic correspondences, which can be projected back to the 3D shapes, producing a raw matching that is inaccurate and inconsistent between different viewpoints. These correspondences are refined and distilled into an inter-surface map by a dedicated optimization scheme, which promotes bijectivity and continuity of the output map. We illustrate that our approach can generate semantic surface-to-surface maps, eliminating manual annotations or any 3D training data requirement. Furthermore, it proves effective in scenarios with high semantic complexity, where objects are non-isometrically related, as well as in situations where they are nearly isometric.

Sanjeev Muralikrishnan, Niladri Shekhar Dutt, Siddhartha Chaudhuri et al.

We introduce Temporal Residual Jacobians as a novel representation to enable data-driven motion transfer. Our approach does not assume access to any rigging or intermediate shape keyframes, produces geometrically and temporally consistent motions, and can be used to transfer long motion sequences. Central to our approach are two coupled neural networks that individually predict local geometric and temporal changes that are subsequently integrated, spatially and temporally, to produce the final animated meshes. The two networks are jointly trained, complement each other in producing spatial and temporal signals, and are supervised directly with 3D positional information. During inference, in the absence of keyframes, our method essentially solves a motion extrapolation problem. We test our setup on diverse meshes (synthetic and scanned shapes) to demonstrate its superiority in generating realistic and natural-looking animations on unseen body shapes against SoTA alternatives. Supplemental video and code are available at https://temporaljacobians.github.io/ .

Rameen Abdal, Peihao Zhu, Niloy J. Mitra et al.

Image editing using a pretrained StyleGAN generator has emerged as a powerful paradigm for facial editing, providing disentangled controls over age, expression, illumination, etc. However, the approach cannot be directly adopted for video manipulations. We hypothesize that the main missing ingredient is the lack of fine-grained and disentangled control over face location, face pose, and local facial expressions. In this work, we demonstrate that such a fine-grained control is indeed achievable using pretrained StyleGAN by working across multiple (latent) spaces (namely, the positional space, the W+ space, and the S space) and combining the optimization results across the multiple spaces. Building on this enabling component, we introduce Video2StyleGAN that takes a target image and driving video(s) to reenact the local and global locations and expressions from the driving video in the identity of the target image. We evaluate the effectiveness of our method over multiple challenging scenarios and demonstrate clear improvements over alternative approaches.

Yu-Shiang Wong, Niloy J. Mitra

A long-standing goal in scene understanding is to obtain interpretable and editable representations that can be directly constructed from a raw monocular RGB-D video, without requiring specialized hardware setup or priors. The problem is significantly more challenging in the presence of multiple moving and/or deforming objects. Traditional methods have approached the setup with a mix of simplifications, scene priors, pretrained templates, or known deformation models. The advent of neural representations, especially neural implicit representations and radiance fields, opens the possibility of end-to-end optimization to collectively capture geometry, appearance, and object motion. However, current approaches produce global scene encoding, assume multiview capture with limited or no motion in the scenes, and do not facilitate easy manipulation beyond novel view synthesis. In this work, we introduce a factored neural scene representation that can directly be learned from a monocular RGB-D video to produce object-level neural presentations with an explicit encoding of object movement (e.g., rigid trajectory) and/or deformations (e.g., nonrigid movement). We evaluate ours against a set of neural approaches on both synthetic and real data to demonstrate that the representation is efficient, interpretable, and editable (e.g., change object trajectory). Code and data are available at http://geometry.cs.ucl.ac.uk/projects/2023/factorednerf .

Pradyumna Reddy, Paul Guerrero, Niloy J. Mitra

Finding an unsupervised decomposition of an image into individual objects is a key step to leverage compositionality and to perform symbolic reasoning. Traditionally, this problem is solved using amortized inference, which does not generalize beyond the scope of the training data, may sometimes miss correct decompositions, and requires large amounts of training data. We propose finding a decomposition using direct, unamortized optimization, via a combination of a gradient-based optimization for differentiable object properties and global search for non-differentiable properties. We show that using direct optimization is more generalizable, misses fewer correct decompositions, and typically requires less data than methods based on amortized inference. This highlights a weakness of the current prevalent practice of using amortized inference that can potentially be improved by integrating more direct optimization elements.

Sanjeev Muralikrishnan, Chun-Hao Paul Huang, Duygu Ceylan et al.

Morphable models are fundamental to numerous human-centered processes as they offer a simple yet expressive shape space. Creating such morphable models, however, is both tedious and expensive. The main challenge is establishing dense correspondences across raw scans that capture sufficient shape variation. This is often addressed using a mix of significant manual intervention and non-rigid registration. We observe that creating a shape space and solving for dense correspondence are tightly coupled -- while dense correspondence is needed to build shape spaces, an expressive shape space provides a reduced dimensional space to regularize the search. We introduce BLiSS, a method to solve both progressively. Starting from a small set of manually registered scans to bootstrap the process, we enrich the shape space and then use that to get new unregistered scans into correspondence automatically. The critical component of BLiSS is a non-linear deformation model that captures details missed by the low-dimensional shape space, thus allowing progressive enrichment of the space.

Corentin Salaün, Xingchang Huang, Iliyan Georgiev et al.

We introduce a theoretical and practical framework for efficient importance sampling of mini-batch samples for gradient estimation from single and multiple probability distributions. To handle noisy gradients, our framework dynamically evolves the importance distribution during training by utilizing a self-adaptive metric. Our framework combines multiple, diverse sampling distributions, each tailored to specific parameter gradients. This approach facilitates the importance sampling of vector-valued gradient estimation. Rather than naively combining multiple distributions, our framework involves optimally weighting data contribution across multiple distributions. This adapted combination of multiple importance yields superior gradient estimates, leading to faster training convergence. We demonstrate the effectiveness of our approach through empirical evaluations across a range of optimization tasks like classification and regression on both image and point cloud datasets.

Haocheng Yuan, Jing Xu, Hao Pan et al.

CAD programs are a popular way to compactly encode shapes as a sequence of operations that are easy to parametrically modify. However, without sufficient semantic comments and structure, such programs can be challenging to understand, let alone modify. We introduce the problem of semantic commenting CAD programs, wherein the goal is to segment the input program into code blocks corresponding to semantically meaningful shape parts and assign a semantic label to each block. We solve the problem by combining program parsing with visual-semantic analysis afforded by recent advances in foundational language and vision models. Specifically, by executing the input programs, we create shapes, which we use to generate conditional photorealistic images to make use of semantic annotators for such images. We then distill the information across the images and link back to the original programs to semantically comment on them. Additionally, we collected and annotated a benchmark dataset, CADTalk, consisting of 5,288 machine-made programs and 45 human-made programs with ground truth semantic comments. We extensively evaluated our approach, compared it to a GPT-based baseline, and an open-set shape segmentation baseline, and reported an 83.24% accuracy on the new CADTalk dataset. Code and data: https://enigma-li.github.io/CADTalk/.

Corentin Salaün, Xingchang Huang, Iliyan Georgiev et al.

Machine learning optimization often depends on stochastic gradient descent, where the precision of gradient estimation is vital for model performance. Gradients are calculated from mini-batches formed by uniformly selecting data samples from the training dataset. However, not all data samples contribute equally to gradient estimation. To address this, various importance sampling strategies have been developed to prioritize more significant samples. Despite these advancements, all current importance sampling methods encounter challenges related to computational efficiency and seamless integration into practical machine learning pipelines. In this work, we propose a practical algorithm that efficiently computes data importance on-the-fly during training, eliminating the need for dataset preprocessing. We also introduce a novel metric based on the derivative of the loss w.r.t. the network output, designed for mini-batch importance sampling. Our metric prioritizes influential data points, thereby enhancing gradient estimation accuracy. We demonstrate the effectiveness of our approach across various applications. We first perform classification and regression tasks to demonstrate improvements in accuracy. Then, we show how our approach can also be used for online data pruning by identifying and discarding data samples that contribute minimally towards the training loss. This significantly reduce training time with negligible loss in the accuracy of the model.

Niladri Shekhar Dutt, Zifan Shi, Paul Guerrero et al.

Tokenization is a fundamental technique in the generative modeling of various modalities. In particular, it plays a critical role in autoregressive (AR) models, which have recently emerged as a compelling option for 3D generation. However, optimal tokenization of 3D shapes remains an open question. State-of-the-art (SOTA) methods primarily rely on geometric level-of-detail (LoD) hierarchies, originally designed for rendering and compression. These spatial hierarchies are often token-inefficient and lack semantic coherence for AR modeling. We propose Level-of-Semantics Tokenization (LoST), which orders tokens by semantic salience, such that early prefixes decode into complete, plausible shapes that possess principal semantics, while subsequent tokens refine instance-specific geometric and semantic details. To train LoST, we introduce Relational Inter-Distance Alignment (RIDA), a novel 3D semantic alignment loss that aligns the relational structure of the 3D shape latent space with that of the semantic DINO feature space. Experiments show that LoST achieves SOTA reconstruction, surpassing previous LoD-based 3D shape tokenizers by large margins on both geometric and semantic reconstruction metrics. Moreover, LoST achieves efficient, high-quality AR 3D generation and enables downstream tasks like semantic retrieval, while using only 0.1%-10% of the tokens needed by prior AR models.

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.

Haocheng Yuan, Adrien Bousseau, Hao Pan et al.

Differentiable rendering is a key ingredient for inverse rendering and machine learning, as it allows to optimize scene parameters (shape, materials, lighting) to best fit target images. Differentiable rendering requires that each scene parameter relates to pixel values through differentiable operations. While 3D mesh rendering algorithms have been implemented in a differentiable way, these algorithms do not directly extend to Constructive-Solid-Geometry (CSG), a popular parametric representation of shapes, because the underlying boolean operations are typically performed with complex black-box mesh-processing libraries. We present an algorithm, DiffCSG, to render CSG models in a differentiable manner. Our algorithm builds upon CSG rasterization, which displays the result of boolean operations between primitives without explicitly computing the resulting mesh and, as such, bypasses black-box mesh processing. We describe how to implement CSG rasterization within a differentiable rendering pipeline, taking special care to apply antialiasing along primitive intersections to obtain gradients in such critical areas. Our algorithm is simple and fast, can be easily incorporated into modern machine learning setups, and enables a range of applications for computer-aided design, including direct and image-based editing of CSG primitives. Code and data: https://yyyyyhc.github.io/DiffCSG/.

Muhammed Burak Kizil, Enes Sanli, Niloy J. Mitra et al.

Video generation has achieved remarkable progress in visual fidelity and controllability, enabling conditioning on text, layout, or motion. Among these, motion control - specifying object dynamics and camera trajectories - is essential for composing complex, cinematic scenes, yet existing interfaces remain limited. We introduce LAMP that leverages large language models (LLMs) as motion planners to translate natural language descriptions into explicit 3D trajectories for dynamic objects and (relatively defined) cameras. LAMP defines a motion domain-specific language (DSL), inspired by cinematography conventions. By harnessing program synthesis capabilities of LLMs, LAMP generates structured motion programs from natural language, which are deterministically mapped to 3D trajectories. We construct a large-scale procedural dataset pairing natural text descriptions with corresponding motion programs and 3D trajectories. Experiments demonstrate LAMP's improved performance in motion controllability and alignment with user intent compared to state-of-the-art alternatives establishing the first framework for generating both object and camera motions directly from natural language specifications.

Marie-Julie Rakotosaona, Noam Aigerman, Niloy Mitra et al.

Triangle meshes remain the most popular data representation for surface geometry. This ubiquitous representation is essentially a hybrid one that decouples continuous vertex locations from the discrete topological triangulation. Unfortunately, the combinatorial nature of the triangulation prevents taking derivatives over the space of possible meshings of any given surface. As a result, to date, mesh processing and optimization techniques have been unable to truly take advantage of modular gradient descent components of modern optimization frameworks. In this work, we present a differentiable surface triangulation that enables optimization for any per-vertex or per-face differentiable objective function over the space of underlying surface triangulations. Our method builds on the result that any 2D triangulation can be achieved by a suitably perturbed weighted Delaunay triangulation. We translate this result into a computational algorithm by proposing a soft relaxation of the classical weighted Delaunay triangulation and optimizing over vertex weights and vertex locations. We extend the algorithm to 3D by decomposing shapes into developable sets and differentiably meshing each set with suitable boundary constraints. We demonstrate the efficacy of our method on various planar and surface meshes on a range of difficult-to-optimize objective functions. Our code can be found online: https://github.com/mrakotosaon/diff-surface-triangulation.

Marie-Julie Rakotosaona, Paul Guerrero, Noam Aigerman et al.

We present a method for reconstructing triangle meshes from point clouds. Existing learning-based methods for mesh reconstruction mostly generate triangles individually, making it hard to create manifold meshes. We leverage the properties of 2D Delaunay triangulations to construct a mesh from manifold surface elements. Our method first estimates local geodesic neighborhoods around each point. We then perform a 2D projection of these neighborhoods using a learned logarithmic map. A Delaunay triangulation in this 2D domain is guaranteed to produce a manifold patch, which we call a Delaunay surface element. We synchronize the local 2D projections of neighboring elements to maximize the manifoldness of the reconstructed mesh. Our results show that we achieve better overall manifoldness of our reconstructed meshes than current methods to reconstruct meshes with arbitrary topology. Our code, data and pretrained models can be found online: https://github.com/mrakotosaon/dse-meshing

Xuelin Chen, Daniel Cohen-Or, Baoquan Chen et al.

In this paper, we leverage advances in neural networks towards forming a neural rendering for controllable image generation, and thereby bypassing the need for detailed modeling in conventional graphics pipeline. To this end, we present Neural Graphics Pipeline (NGP), a hybrid generative model that brings together neural and traditional image formation models. NGP decomposes the image into a set of interpretable appearance feature maps, uncovering direct control handles for controllable image generation. To form an image, NGP generates coarse 3D models that are fed into neural rendering modules to produce view-specific interpretable 2D maps, which are then composited into the final output image using a traditional image formation model. Our approach offers control over image generation by providing direct handles controlling illumination and camera parameters, in addition to control over shape and appearance variations. The key challenge is to learn these controls through unsupervised training that links generated coarse 3D models with unpaired real images via neural and traditional (e.g., Blinn- Phong) rendering functions, without establishing an explicit correspondence between them. We demonstrate the effectiveness of our approach on controllable image generation of single-object scenes. We evaluate our hybrid modeling framework, compare with neural-only generation methods (namely, DCGAN, LSGAN, WGAN-GP, VON, and SRNs), report improvement in FID scores against real images, and demonstrate that NGP supports direct controls common in traditional forward rendering. Code is available at http://geometry.cs.ucl.ac.uk/projects/2021/ngp.

Anran Qi, Changjian Li, Adrien Bousseau et al.

We address image-to-video generation with explicit user control over the final frame's disoccluded regions. Current image-to-video pipelines produce plausible motion but struggle to generate predictable, articulated motions while enforcing user-specified content in newly revealed areas. Our key idea is to separate motion specification from appearance synthesis: we introduce a lightweight, user-editable Proxy Dynamic Graph (PDG) that deterministically yet approximately drives part motion, while a frozen diffusion prior is used to synthesize plausible appearance that follows that motion. In our training-free pipeline, the user loosely annotates and reposes a PDG, from which we compute a dense motion flow to leverage diffusion as a motion-guided shader. We then let the user edit appearance in the disoccluded areas of the image, and exploit the visibility information encoded by the PDG to perform a latent-space composite that reconciles motion with user intent in these areas. This design yields controllable articulation and user control over disocclusions without fine-tuning. We demonstrate clear advantages against state-of-the-art alternatives towards images turned into short videos of articulated objects, furniture, vehicles, and deformables. Our method mixes generative control, in the form of loose pose and structure, with predictable controls, in the form of appearance specification in the final frame in the disoccluded regions, unlocking a new image-to-video workflow. Code will be released on acceptance. Project page: https://anranqi.github.io/beyond-visible.github.io/

Remy Sabathier, David Novotny, Niloy J. Mitra et al.

Generating animated 3D objects is at the heart of many applications, yet most advanced works are typically difficult to apply in practice because of their limited setup, their long runtime, or their limited quality. We introduce ActionMesh, a generative model that predicts production-ready 3D meshes "in action" in a feed-forward manner. Drawing inspiration from early video models, our key insight is to modify existing 3D diffusion models to include a temporal axis, resulting in a framework we dubbed "temporal 3D diffusion". Specifically, we first adapt the 3D diffusion stage to generate a sequence of synchronized latents representing time-varying and independent 3D shapes. Second, we design a temporal 3D autoencoder that translates a sequence of independent shapes into the corresponding deformations of a pre-defined reference shape, allowing us to build an animation. Combining these two components, ActionMesh generates animated 3D meshes from different inputs like a monocular video, a text description, or even a 3D mesh with a text prompt describing its animation. Besides, compared to previous approaches, our method is fast and produces results that are rig-free and topology consistent, hence enabling rapid iteration and seamless applications like texturing and retargeting. We evaluate our model on standard video-to-4D benchmarks (Consistent4D, Objaverse) and report state-of-the-art performances on both geometric accuracy and temporal consistency, demonstrating that our model can deliver animated 3D meshes with unprecedented speed and quality.

Shariq Farooq Bhat, Niloy J. Mitra, Peter Wonka

We present LooseControl to allow generalized depth conditioning for diffusion-based image generation. ControlNet, the SOTA for depth-conditioned image generation, produces remarkable results but relies on having access to detailed depth maps for guidance. Creating such exact depth maps, in many scenarios, is challenging. This paper introduces a generalized version of depth conditioning that enables many new content-creation workflows. Specifically, we allow (C1) scene boundary control for loosely specifying scenes with only boundary conditions, and (C2) 3D box control for specifying layout locations of the target objects rather than the exact shape and appearance of the objects. Using LooseControl, along with text guidance, users can create complex environments (e.g., rooms, street views, etc.) by specifying only scene boundaries and locations of primary objects. Further, we provide two editing mechanisms to refine the results: (E1) 3D box editing enables the user to refine images by changing, adding, or removing boxes while freezing the style of the image. This yields minimal changes apart from changes induced by the edited boxes. (E2) Attribute editing proposes possible editing directions to change one particular aspect of the scene, such as the overall object density or a particular object. Extensive tests and comparisons with baselines demonstrate the generality of our method. We believe that LooseControl can become an important design tool for easily creating complex environments and be extended to other forms of guidance channels. Code and more information are available at https://shariqfarooq123.github.io/loose-control/ .

Hyeonho Jeong, Chun-Hao Paul Huang, Jong Chul Ye et al.

While recent foundational video generators produce visually rich output, they still struggle with appearance drift, where objects gradually degrade or change inconsistently across frames, breaking visual coherence. We hypothesize that this is because there is no explicit supervision in terms of spatial tracking at the feature level. We propose Track4Gen, a spatially aware video generator that combines video diffusion loss with point tracking across frames, providing enhanced spatial supervision on the diffusion features. Track4Gen merges the video generation and point tracking tasks into a single network by making minimal changes to existing video generation architectures. Using Stable Video Diffusion as a backbone, Track4Gen demonstrates that it is possible to unify video generation and point tracking, which are typically handled as separate tasks. Our extensive evaluations show that Track4Gen effectively reduces appearance drift, resulting in temporally stable and visually coherent video generation. Project page: hyeonho99.github.io/track4gen

Remy Sabathier, Niloy J. Mitra, David Novotny

We present a method to build animatable dog avatars from monocular videos. This is challenging as animals display a range of (unpredictable) non-rigid movements and have a variety of appearance details (e.g., fur, spots, tails). We develop an approach that links the video frames via a 4D solution that jointly solves for animal's pose variation, and its appearance (in a canonical pose). To this end, we significantly improve the quality of template-based shape fitting by endowing the SMAL parametric model with Continuous Surface Embeddings, which brings image-to-mesh reprojection constaints that are denser, and thus stronger, than the previously used sparse semantic keypoint correspondences. To model appearance, we propose an implicit duplex-mesh texture that is defined in the canonical pose, but can be deformed using SMAL pose coefficients and later rendered to enforce a photometric compatibility with the input video frames. On the challenging CoP3D and APTv2 datasets, we demonstrate superior results (both in terms of pose estimates and predicted appearance) to existing template-free (RAC) and template-based approaches (BARC, BITE).

Gabrielle Littlefair, Niladri Shekhar Dutt, Niloy J. Mitra

Interior design involves the careful selection and arrangement of objects to create an aesthetically pleasing, functional, and harmonized space that aligns with the client's design brief. This task is particularly challenging, as a successful design must not only incorporate all the necessary objects in a cohesive style, but also ensure they are arranged in a way that maximizes accessibility, while adhering to a variety of affordability and usage considerations. Data-driven solutions have been proposed, but these are typically room- or domain-specific and lack explainability in their design design considerations used in producing the final layout. In this paper, we investigate if large language models (LLMs) can be directly utilized for interior design. While we find that LLMs are not yet capable of generating complete layouts, they can be effectively leveraged in a structured manner, inspired by the workflow of interior designers. By systematically probing LLMs, we can reliably generate a list of objects along with relevant constraints that guide their placement. We translate this information into a design layout graph, which is then solved using an off-the-shelf constrained optimization setup to generate the final layouts. We benchmark our algorithm in various design configurations against existing LLM-based methods and human designs, and evaluate the results using a variety of quantitative and qualitative metrics along with user studies. In summary, we demonstrate that LLMs, when used in a structured manner, can effectively generate diverse high-quality layouts, making them a viable solution for creating large-scale virtual scenes. Project webpage at https://flairgpt.github.io/

Karran Pandey, Matheus Gadelha, Yannick Hold-Geoffroy et al.

Predicting diverse object motions from a single static image remains challenging, as current video generation models often entangle object movement with camera motion and other scene changes. While recent methods can predict specific motions from motion arrow input, they rely on synthetic data and predefined motions, limiting their application to complex scenes. We introduce Motion Modes, a training-free approach that explores a pre-trained image-to-video generator's latent distribution to discover various distinct and plausible motions focused on selected objects in static images. We achieve this by employing a flow generator guided by energy functions designed to disentangle object and camera motion. Additionally, we use an energy inspired by particle guidance to diversify the generated motions, without requiring explicit training data. Experimental results demonstrate that Motion Modes generates realistic and varied object animations, surpassing previous methods and even human predictions regarding plausibility and diversity. Project Webpage: https://motionmodes.github.io/

Niladri Shekhar Dutt, Duygu Ceylan, Niloy J. Mitra

Retouching is an essential task in post-manipulation of raw photographs. Generative editing, guided by text or strokes, provides a new tool accessible to users but can easily change the identity of the original objects in unacceptable and unpredictable ways. In contrast, although traditional procedural edits, as commonly supported by photoediting tools (e.g., Gimp, Lightroom), are conservative, they are still preferred by professionals. Unfortunately, professional quality retouching involves many individual procedural editing operations that is challenging to plan for most novices. In this paper, we ask if a multimodal large language model (MLLM) can be taught to critique raw photographs, suggest suitable remedies, and finally realize them with a given set of pre-authored procedural image operations. We demonstrate that MLLMs can be first made aware of the underlying image processing operations, by training them to solve specially designed visual puzzles. Subsequently, such an operation-aware MLLM can both plan and propose edit sequences. To facilitate training, given a set of expert-edited photos, we synthesize a reasoning dataset by procedurally manipulating the expert edits and then grounding a pretrained LLM on the visual adjustments, to synthesize reasoning for finetuning. The proposed retouching operations are, by construction, understandable by the users, preserve object details and resolution, and can be optionally overridden. We evaluate our setup on a variety of test examples and show advantages, in terms of explainability and identity preservation, over existing generative and other procedural alternatives. Code, data, models, and supplementary results can be found via our project website at https://monetgpt.github.io.

Hao Xu, Yinqiao Wang, Niloy J. Mitra et al.

Hand shadow art is a captivating art form, creatively using hand shadows to reproduce expressive shapes on the wall. In this work, we study an inverse problem: given a target shape, find the poses of left and right hands that together best produce a shadow resembling the input. This problem is nontrivial, since the design space of 3D hand poses is huge while being restrictive due to anatomical constraints. Also, we need to attend to the input's shape and crucial features, though the input is colorless and textureless. To meet these challenges, we design Hand-Shadow Poser, a three-stage pipeline, to decouple the anatomical constraints (by hand) and semantic constraints (by shadow shape): (i) a generative hand assignment module to explore diverse but reasonable left/right-hand shape hypotheses; (ii) a generalized hand-shadow alignment module to infer coarse hand poses with a similarity-driven strategy for selecting hypotheses; and (iii) a shadow-feature-aware refinement module to optimize the hand poses for physical plausibility and shadow feature preservation. Further, we design our pipeline to be trainable on generic public hand data, thus avoiding the need for any specialized training dataset. For method validation, we build a benchmark of 210 diverse shadow shapes of varying complexity and a comprehensive set of metrics, including a novel DINOv2-based evaluation metric. Through extensive comparisons with multiple baselines and user studies, our approach is demonstrated to effectively generate bimanual hand poses for a large variety of hand shapes for over 85% of the benchmark cases.

Souhaib Attaiki, Paul Guerrero, Duygu Ceylan et al.

We train a feed-forward text-to-3D diffusion generator for human characters using only single-view 2D data for supervision. Existing 3D generative models cannot yet match the fidelity of image or video generative models. State-of-the-art 3D generators are either trained with explicit 3D supervision and are thus limited by the volume and diversity of existing 3D data. Meanwhile, generators that can be trained with only 2D data as supervision typically produce coarser results, cannot be text-conditioned, or must revert to test-time optimization. We observe that GAN- and diffusion-based generators have complementary qualities: GANs can be trained efficiently with 2D supervision to produce high-quality 3D objects but are hard to condition on text. In contrast, denoising diffusion models can be conditioned efficiently but tend to be hard to train with only 2D supervision. We introduce GANFusion, which starts by generating unconditional triplane features for 3D data using a GAN architecture trained with only single-view 2D data. We then generate random samples from the GAN, caption them, and train a text-conditioned diffusion model that directly learns to sample from the space of good triplane features that can be decoded into 3D objects.

Animesh Karnewar, Roman Shapovalov, Tom Monnier et al. · meta-ai

Encoding information from 2D views of an object into a 3D representation is crucial for generalized 3D feature extraction. Such features can then enable 3D reconstruction, 3D generation, and other applications. We propose GOEmbed (Gradient Origin Embeddings) that encodes input 2D images into any 3D representation, without requiring a pre-trained image feature extractor; unlike typical prior approaches in which input images are either encoded using 2D features extracted from large pre-trained models, or customized features are designed to handle different 3D representations; or worse, encoders may not yet be available for specialized 3D neural representations such as MLPs and hash-grids. We extensively evaluate our proposed GOEmbed under different experimental settings on the OmniObject3D benchmark. First, we evaluate how well the mechanism compares against prior encoding mechanisms on multiple 3D representations using an illustrative experiment called Plenoptic-Encoding. Second, the efficacy of the GOEmbed mechanism is further demonstrated by achieving a new SOTA FID of 22.12 on the OmniObject3D generation task using a combination of GOEmbed and DFM (Diffusion with Forward Models), which we call GOEmbedFusion. Finally, we evaluate how the GOEmbed mechanism bolsters sparse-view 3D reconstruction pipelines.

Lilian Welschinger, Yilin Liu, Zican Wang et al.

Solving partial differential equations (PDEs) on shapes underpins many shape analysis and engineering tasks; yet, prevailing PDE solvers operate on polygonal/triangle meshes while modern 3D assets increasingly live as neural representations. This mismatch leaves no suitable method to solve surface PDEs directly within the neural domain, forcing explicit mesh extraction or per-instance residual training, preventing end-to-end workflows. We present a novel, mesh-free formulation that learns a local update operator conditioned on neural (local) shape attributes, enabling surface PDEs to be solved directly where the (neural) data lives. The operator integrates naturally with prevalent neural surface representations, is trained once on a single representative shape, and generalizes across shape and topology variations, enabling accurate, fast inference without explicit meshing or per-instance optimization while preserving differentiability. Across analytic benchmarks (heat equation and Poisson solve on sphere) and real neural assets across different representations, our method slightly outperforms CPM while remaining reasonably close to FEM, and, to our knowledge, delivers the first end-to-end pipeline that solves surface PDEs on both neural and classical surface representations. Code will be released on acceptance.

Rishabh Kabra, Maks Ovsjanikov, Drew A. Hudson et al.

Pre-trained vision encoders like DINOv2 have demonstrated exceptional performance on unimodal tasks. However, we observe that their feature representations are poorly aligned across different modalities. For instance, the feature embedding for an RGB image and its corresponding depth map of the same scene exhibit a cosine similarity that is nearly identical to that of two random, unrelated images. To address this, we propose the Omnivorous Vision Encoder, a novel framework that learns a modality-agnostic feature space. We train the encoder with a dual objective: first, to maximize the feature alignment between different modalities of the same scene; and second, a distillation objective that anchors the learned representations to the output of a fully frozen teacher such as DINOv2. The resulting student encoder becomes "omnivorous" by producing a consistent, powerful embedding for a given scene, regardless of the input modality (RGB, Depth, Segmentation, etc.). This approach enables robust cross-modal understanding while retaining the discriminative semantics of the original foundation model.

Sanjeev Muralikrishnan, Niladri Shekhar Dutt, Niloy J. Mitra

Animation retargetting applies sparse motion description (e.g., keypoint sequences) to a character mesh to produce a semantically plausible and temporally coherent full-body mesh sequence. Existing approaches come with restrictions -- they require access to template-based shape priors or artist-designed deformation rigs, suffer from limited generalization to unseen motion and/or shapes, or exhibit motion jitter. We propose Self-supervised Motion Fields (SMF), a self-supervised framework that is trained with only sparse motion representations, without requiring dataset-specific annotations, templates, or rigs. At the heart of our method are Kinetic Codes, a novel autoencoder-based sparse motion encoding, that exposes a semantically rich latent space, simplifying large-scale training. Our architecture comprises dedicated spatial and temporal gradient predictors, which are jointly trained in an end-to-end fashion. The combined network, regularized by the Kinetic Codes' latent space, has good generalization across both unseen shapes and new motions. We evaluated our method on unseen motion sampled from AMASS, D4D, Mixamo, and raw monocular video for animation transfer on various characters with varying shapes and topology. We report a new SoTA on the AMASS dataset in the context of generalization to unseen motion. Code, weights, and supplementary are available on the project webpage at https://motionfields.github.io/

Remy Sabathier, Niloy J. Mitra, David Novotny

Reconstructing dynamic assets from video data is central to many in computer vision and graphics tasks. Existing 4D reconstruction approaches are limited by category-specific models or slow optimization-based methods. Inspired by the recent Large Reconstruction Model (LRM), we present the Large Interpolation Model (LIM), a transformer-based feed-forward solution, guided by a novel causal consistency loss, for interpolating implicit 3D representations across time. Given implicit 3D representations at times $t_0$ and $t_1$, LIM produces a deformed shape at any continuous time $t\in[t_0,t_1]$, delivering high-quality interpolated frames in seconds. Furthermore, LIM allows explicit mesh tracking across time, producing a consistently uv-textured mesh sequence ready for integration into existing production pipelines. We also use LIM, in conjunction with a diffusion-based multiview generator, to produce dynamic 4D reconstructions from monocular videos. We evaluate LIM on various dynamic datasets, benchmarking against image-space interpolation methods (e.g., FiLM) and direct triplane linear interpolation, and demonstrate clear advantages. In summary, LIM is the first feed-forward model capable of high-speed tracked 4D asset reconstruction across diverse categories.

R. Kenny Jones, Paul Guerrero, Niloy J. Mitra et al.

We present ShapeLib, the first method that leverages the priors of LLMs to design libraries of programmatic 3D shape abstractions. Our system accepts two forms of design intent: text descriptions of functions to include in the library and a seed set of exemplar shapes. We discover abstractions that match this design intent with a guided LLM workflow that first proposes, and then validates, different ways of applying and implementing functions. We learn recognition networks that map shapes to programs with these newly discovered abstractions by training on data produced by LLM authored synthetic data generation procedures. Across modeling domains (split by shape category), we find that LLMs, when thoughtfully combined with geometric reasoning, can be guided to author a library of abstraction functions that generalize to shapes outside of the seed set. This framework addresses a long-standing shape analysis problem of how to discover reusable abstraction functions while exposing interpretable, semantically aligned interfaces. We find that ShapeLib provides distinct advantages over prior alternative abstraction discovery works in terms of generalization, usability, and maintaining plausibility under manipulation. Finally, we demonstrate that ShapeLib's abstraction functions unlock a number of downstream applications, combining LLM reasoning over shape programs with geometry processing to support shape editing and generation.

Chun-Hao Paul Huang, Niloy Mitra, Hyeonho Jeong et al.

Emergent capabilities of image generators have led to many impactful zero- or few-shot applications. Inspired by this success, we investigate whether video generators similarly exhibit 3D-awareness. Using structure-from-motion as a 3D-aware task, we test if intermediate features of a video generator - OpenSora in our case - can support camera pose estimation. Surprisingly, at first, we only find a weak correlation between the two tasks. Deeper investigation reveals that although the video generator produces plausible video frames, the frames themselves are not truly 3D-consistent. Instead, we propose to jointly train for the two tasks, using photometric generation and 3D aware errors. Specifically, we find that SoTA video generation and camera pose estimation (i.e.,DUSt3R [79]) networks share common structures, and propose an architecture that unifies the two. The proposed unified model, named \nameMethod, produces camera pose estimates with competitive quality while producing 3D-consistent videos. In summary, we propose the first unified video generator that is 3D-consistent, generates realistic video frames, and can potentially be repurposed for other 3D-aware tasks.

Rishabh Kabra, Drew A. Hudson, Sjoerd van Steenkiste et al.

We introduce a hierarchical probabilistic approach to go from a 2D image to multiview 3D: a diffusion "prior" predicts the unseen 3D geometry, which then conditions a diffusion "decoder" to generate novel views of the subject. We use a pointmap-based geometric representation to coordinate the generation of multiple target views simultaneously. We construct a predictable distribution of geometric features per target view to enable learnability across examples, and generalization to arbitrary inputs images. Our modular, geometry-driven approach to novel-view synthesis (called "unPIC") beats competing baselines such as CAT3D, EscherNet, Free3D, and One-2-3-45 on held-out objects from ObjaverseXL, as well as unseen real-world objects from Google Scanned Objects, Amazon Berkeley Objects, and the Digital Twin Catalog.