Gaussian Splatting have demonstrated remarkable novel view synthesis performance at high rendering frame rates. Optimization-based inverse rendering within complex capture scenarios remains however a challenging problem. A particular case is modelling complex surface light interactions for highly reflective scenes, which results in intricate high frequency specular radiance components. We hypothesize that such challenging settings can benefit from increased representation power. We hence propose a method that tackles this issue through a geometrically and physically grounded Gaussian Splatting borne radiance field, where normals and material properties are spatially variable in the primitive's local space. Using per-primitive texture maps for this purpose, we also propose to harness the GPU hardware to accelerate rendering at test time via unified material texture atlas. Code will be available at TextureSplat.

Abstract Recent advancements in Gaussian Splatting have enabled increasingly accurate reconstruction of photorealistic head avatars, opening the door to numerous applications in visual effects, videoconferencing, and virtual reality. This, however, comes with the lack of intuitive editability offered by traditional triangle mesh‐based methods. In contrast, we propose a method that combines the accuracy and fidelity of 2D Gaussian Splatting with the intuitiveness of UV texture mapping. By embedding each canonical Gaussian primitive's local frame into a patch in the UV space of a template mesh in a computationally efficient manner, we reconstruct continuous editable material head textures from a single monocular video on a conventional UV domain. Furthermore, we leverage an efficient physically based reflectance model to enable relighting and editing of these intrinsic material maps. Through extensive comparisons with state‐of‐the‐art methods, we demonstrate the accuracy of our reconstructions, the quality of our relighting results, and the ability to provide intuitive controls for modifying an avatar's appearance and geometry via texture mapping without additional optimization.

The growing popularity of Contrastive Language-Image Pretraining (CLIP) has led to its widespread application in various visual downstream tasks. To enhance CLIP’s effectiveness and versatility, efficient few-shot adaptation techniques have been widely adopted. Among these approaches, training-free methods, particularly caching methods exemplified by Tip-Adapter, have gained attention for their lightweight adaptation without the need for additional fine-tuning. In this paper, we revisit Tip-Adapter from a kernel perspective, showing that caching methods function as local adapters and are connected to a well-established kernel literature. Drawing on this insight, we offer a theoretical understanding of how these methods operate and suggest multiple avenues for enhancing the Tip-Adapter baseline. Notably, our analysis shows the importance of incorporating global information in local adapters. Therefore, we subsequently propose a global method that learns a proximal regularizer in a reproducing kernel Hilbert space (RKHS) using CLIP as a base learner. Our method, which we call ProKeR (Proximal Kernel ridge Regression), has a closed form solution and achieves state-of-the-art performances across 11 datasets in the standard few-shot adaptation benchmark. Code is available at https://ybendou.github.io/ProKeR/

We consider the challenging problem of learning Signed Distance Functions (SDF) from sparse and noisy 3D point clouds. In contrast to recent methods that depend on smoothness priors, our method, rooted in a distributionally robust optimization (DRO) framework, incorporates a regularization term that leverages samples from the uncertainty regions of the model to improve the learned SDFs. Thanks to tractable dual formulations, we show that this framework enables a stable and efficient optimization of SDFs in the absence of ground truth supervision. Using a variety of synthetic and real data evaluations from different modalities, we show that our DRO based learning framework can improve SDF learning with respect to baselines and the state-of-the-art methods.

2D Gaussian Splatting (2DGS) has recently emerged as a promising method for novel view synthesis and surface reconstruction, offering better view-consistency and geometric accuracy than volumetric 3DGS. However, 2DGS suffers from severe aliasing artifacts when rendering at different sampling rates than those used during training, limiting its practical applications in scenarios requiring camera zoom or varying fields of view. We identify that these artifacts stem from two key limitations: the lack of frequency constraints in the representation and an ineffective screen-space clamping approach. To address these issues, we present AA-2DGS, an anti-aliased formulation of 2D Gaussian Splatting that maintains its geometric benefits while significantly enhancing rendering quality across different scales. Our method introduces a world-space flat smoothing kernel that constrains the frequency content of 2D Gaussian primitives based on the maximal sampling frequency from training views, effectively eliminating high-frequency artifacts when zooming in. Additionally, we derive a novel object-space Mip filter by leveraging an affine approximation of the ray-splat intersection mapping, which allows us to efficiently apply proper anti-aliasing directly in the local space of each splat. Code will be available at https://github.com/maeyounes/AA-2DGS.

While current state-of-the-art generalizable implicit neural shape models [7], [54] rely on the inductive bias of convolutions, it is still not entirely clear how properties emerging from such biases are compatible with the task of 3D reconstruction from point cloud. We explore an alternative approach to generalizability in this context. We relax the intrinsic model bias (i.e. using MLPs to encode local features as opposed to convolutions) and constrain the hypothesis space instead with an auxiliary regularization related to the reconstruction task, i.e. denoising. The resulting model is the first only-MLP locally conditioned implicit shape reconstruction from point cloud network with fast feed forward inference. Point cloud borne features and denoising offsets are predicted from an exclusively MLP-made network in a single forward pass. A decoder predicts occupancy probabilities for queries anywhere in space by pooling nearby features from the point cloud order-invariantly, guided by denoised relative positional encoding. We outperform the state-of-the-art convolutional method [7] while using half the number of model parameters.

Implicit Neural Representations have gained prominence as a powerful framework for capturing complex data modalities, encompassing a wide range from 3D shapes to images and audio. Within the realm of 3D shape representation, Neural Signed Distance Functions (SDF) have demonstrated remarkable potential in faithfully encoding intricate shape geometry. However, learning SDFs from 3D point clouds in the absence of ground truth supervision remains a very challenging task. In this paper, we propose a method to infer occupancy fields instead of SDFs as they are easier to learn from sparse inputs. We leverage a margin-based uncertainty measure to differentiably sample from the decision boundary of the occupancy function and supervise the sampled boundary points using the input point cloud. We further stabilise the optimization process at the early stages of the training by biasing the occupancy function towards minimal entropy fields while maximizing its entropy at the input point cloud. Through extensive experiments and evaluations, we illustrate the efficacy of our proposed method, highlighting its capacity to improve implicit shape inference with respect to baselines and the state-of-the-art using synthetic and real data.

Implicit Neural Representations have gained prominence as a powerful framework for capturing complex data modalities, encompassing a wide range from 3D shapes to images and audio. Within the realm of 3D shape representation, Neural Signed Distance Functions (SDF) have demonstrated remarkable potential in faithfully encoding intricate shape geometry. However, learning SDFs from sparse 3D point clouds in the absence of ground truth supervision remains a very challenging task. While recent methods rely on smoothness priors to regularize the learning, our method introduces a regularization term that leverages adversarial samples around the shape to improve the learned SDFs. Through extensive experiments and evaluations, we illustrate the efficacy of our proposed method, highlighting its capacity to improve SDF learning with respect to baselines and the state-of-the-art using synthetic and real data.

Feedforward monocular face capture methods seek to reconstruct posed faces from a single image of a person. Current state of the art approaches have the ability to regress parametric 3D face models in real-time across a wide range of identities, lighting conditions and poses by leveraging large image datasets of human faces. These methods however suffer from clear limitations in that the underlying parametric face model only provides a coarse estimation of the face shape, thereby limiting their practical applicability in tasks that require precise 3D reconstruction (aging, face swapping, digital make-up, ...). In this paper, we propose a method for high-precision 3D face capture taking advantage of a collection of unconstrained videos of a subject as prior information. Our proposal builds on a two stage approach. We start with the reconstruction of a detailed 3D face avatar of the person, capturing both precise geometry and appearance from a collection of videos. We then use the encoder from a pre-trained monocular face reconstruction method, substituting its decoder with our personalized model, and proceed with transfer learning on the video collection. Using our pre-estimated image formation model, we obtain a more precise self-supervision objective, enabling improved expression and pose alignment. This results in a trained encoder capable of efficiently regressing pose and expression parameters in real-time from previously unseen images, which combined with our personalized geometry model yields more accurate and high fidelity mesh inference. Through extensive qualitative and quantitative evaluation, we showcase the superiority of our final model as compared to state-of-the-art baselines, and demonstrate its generalization ability to unseen pose, expression and lighting.

We explore a new strategy for few-shot novel view synthesis based on a neural light field representation. Given a target camera pose, an implicit neural network maps each ray to its target pixel’s color directly. The network is conditioned on local ray features generated by coarse volumetric rendering from an explicit 3D feature volume. This volume is built from the input images using a 3D ConvNet. Our method achieves competitive performances on real MVS data with respect to state-of-the-art neural radiance field based competition, while offering a roughly 50 times faster rendering.

This paper aims to improve neural radiance fields (NeRF) from sparse inputs. NeRF achieves photo-realistic renderings when given dense inputs, while its’ performance drops dramatically with the decrease of training views’ number. Our insight is that the standard volumetric rendering of NeRF is prone to over-fitting due to the lack of overall geometry and local neighborhood information from limited inputs. To address this issue, we propose a global sampling strategy with a geometry regularization utilizing warped images as augmented pseudo-views to encourage geometry consistency across multi-views. In addition, we introduce a local patch sampling scheme with a patch-based regularization for appearance consistency. Furthermore, our method exploits depth information for explicit geometry regularization. The proposed approach outperforms existing baselines on real benchmarks DTU datasets from sparse inputs and achieves the state of art results.

Feedforward generalizable models for implicit shape reconstruction from unoriented point cloud present multiple advantages, including high performance and inference speed. However, they still suffer from generalization issues, ranging from underfitting the input point cloud, to misrepresenting samples outside of the training data distribution, or with toplogies unseen at training. We propose here an efficient mechanism to remedy some of these limitations at test time. We combine the inter-shape data prior of the network with an intra-shape regularization prior of a Nyström Kernel Ridge Regression, that we further adapt by fitting its hyperprameters to the current shape. The resulting shape function defined in a shape specific Reproducing Kernel Hilbert Space benefits from desirable stability and efficiency properties and grants a shape adaptive expressiveness-robustness trade-off. We demonstrate the improvement obtained through our method with respect to baselines and the state-of-the-art using synthetic and real data.

We consider the problem of human deformation transfer, where the goal is to retarget poses between different characters. Traditional methods that tackle this problem assume a human pose model to be available and transfer poses between characters using this model. In this work, we take a different approach and transform the identity of a character into a new identity without modifying the character’s pose. This offers the advantage of not having to define equivalences between 3D human poses, which is not straightforward as poses tend to change depending on the identity of the character performing them, and as their meaning is highly contextual. To achieve the deformation transfer, we propose a neural encoder-decoder architecture where only identity information is encoded and where the decoder is conditioned on the pose. We use pose independent representations, such as isometry-invariant shape characteristics, to represent identity features. Our model uses these features to supervise the prediction of offsets from the deformed pose to the result of the transfer. We show experimentally that our method outperforms state-of-the-art methods both quantitatively and qualitatively, and generalises better to poses not seen during training. We also introduce a fine-tuning step that allows to obtain competitive results for extreme identities, and allows to transfer simple clothing.

Convolutional networks have been extremely successful for regular data structures such as 2D images and 3D voxel grids. The transposition to meshes is, however, not straightforward due to their irregular structure. We explore how the dual, face-based representation of triangular meshes can be leveraged as a data structure for graph convolutional networks. In the dual mesh, each node (face) has a fixed number of neighbors, which makes the networks less susceptible to overfitting on the mesh topology, and also allows the use of input features that are naturally defined over faces, such as surface normals and face areas. We evaluate the dual approach on the shape correspondence task on the Faust human shape dataset and variants of it with different mesh topologies. Our experiments show that results of graph convolutional networks improve when defined over the dual rather than primal mesh. Moreover, our models that explicitly leverage the neighborhood regularity of dual meshes allow improving results further while being more robust to changes in the mesh topology.

We propose to improve on graph convolution based approaches for human shape and pose estimation from monocular input, using pixel-aligned local image features. Given a single input color image, existing graph convolutional network (GCN) based techniques for human shape and pose estimation (e.g. [19]) use a single convolutional neural network (CNN) generated global image feature appended to all mesh vertices equally to initialize the GCN stage, which transforms a template T-posed mesh into the target pose. In contrast, we propose for the first time the idea of using local image features per vertex. These features are sampled from the CNN image feature maps by utilizing pixel-to-mesh correspondences generated with DensePose [11]. Our quantitative and qualitative results on standard benchmarks show that using local features improves on global ones and leads to competitive performances with respect to the state-of-the-art.

We present an approach for estimating surface normals from in-the-wild color images of faces. While data-driven strategies have been proposed for single face images, limited available ground truth data makes this problem difficult. To alleviate this issue, we propose a method that can leverage all available image and normal data, whether paired or not, thanks to a novel cross-modal learning architecture. In particular, we enable additional training with single modality data, either color or normal, by using two encoder-decoder networks with a shared latent space. The proposed architecture also enables face details to be transferred between the image and normal domains, given paired data, through skip connections between the image encoder and normal decoder. Core to our approach is a novel module that we call deactivable skip connections, which allows integrating both the auto-encoded and image-to-normal branches within the same architecture that can be trained end-to-end. This allows learning of a rich latent space that can accurately capture the normal information. We compare against state-of-the-art methods and show that our approach can achieve significant improvements, both quantitative and qualitative, with natural face images.

Abstract Deep generative modelling for human body analysis is an emerging problem with many interesting applications. However, the latent space learned by such approaches is typically not interpretable, resulting in less flexibility. In this work, we present deep generative models for human body analysis in which the body pose and the visual appearance are disentangled. Such a disentanglement allows independent manipulation of pose and appearance, and hence enables applications such as pose-transfer without specific training for such a task. Our proposed models, the Conditional-DGPose and the Semi-DGPose, have different characteristics. In the first, body pose labels are taken as conditioners, from a fully-supervised training set. In the second, our structured semi-supervised approach allows for pose estimation to be performed by the model itself and relaxes the need for labelled data. Therefore, the Semi-DGPose aims for the joint understanding and generation of people in images. It is not only capable of mapping images to interpretable latent representations but also able to map these representations back to the image space. We compare our models with relevant baselines, the ClothNet-Body and the Pose Guided Person Generation networks, demonstrating their merits on the Human3.6M, ChictopiaPlus and DeepFashion benchmarks.

We present in this work the first end-to-end deep learning based method that predicts both 3D hand shape and pose from RGB images in the wild. Our network consists of the concatenation of a deep convolutional encoder, and a fixed model-based decoder. Given an input image, and optionally 2D joint detections obtained from an independent CNN, the encoder predicts a set of hand and view parameters. The decoder has two components: A pre-computed articulated mesh deformation hand model that generates a 3D mesh from the hand parameters, and a re-projection module controlled by the view parameters that projects the generated hand into the image domain. We show that using the shape and pose prior knowledge encoded in the hand model within a deep learning framework yields state-of-the-art performance in 3D pose prediction from images on standard benchmarks, and produces geometrically valid and plausible 3D reconstructions. Additionally, we show that training with weak supervision in the form of 2D joint annotations on datasets of images in the wild, in conjunction with full supervision in the form of 3D joint annotations on limited available datasets allows for good generalization to 3D shape and pose predictions on images in the wild.

Data-driven generative 3D face models are used to compactly encode facial shape data into meaningful parametric representations. A desirable property of these models is their ability to effectively decouple natural sources of variation, in particular identity and expression. While factorized representations have been proposed for that purpose, they are still limited in the variability they can capture and may present modeling artifacts when applied to tasks such as expression transfer. In this work, we explore a new direction with Generative Adversarial Networks and show that they contribute to better face modeling performances, especially in decoupling natural factors, while also achieving more diverse samples. To train the model we introduce a novel architecture that combines a 3D generator with a 2D discriminator that leverages conventional CNNs, where the two components are bridged by a geometry mapping layer. We further present a training scheme, based on auxiliary classifiers, to explicitly disentangle identity and expression attributes. Through quantitative and qualitative results on standard face datasets, we illustrate the benefits of our model and demonstrate that it outperforms competing state of the art methods in terms of decoupling and diversity.

We propose a deep generative model of humans in natural images which keeps 2D pose separated from other latent factors of variation, such as background scene and clothing. In contrast to methods that learn generative models of low-dimensional representations, e.g., segmentation masks and 2D skeletons, our single-stage end-to-end conditional-VAEGAN learns directly on the image space. The flexibility of this approach allows the sampling of people with independent variations of pose and appearance. Moreover, it enables the reconstruction of images conditioned to a given posture, allowing, for instance, pose-transfer from one person to another. We validate our method on the Human3.6M dataset and achieve state-of-the-art results on the ChictopiaPlus benchmark. Our model, named Conditional-DGPose, outperforms the closest related work in the literature. It generates more realistic and accurate images regarding both, body posture and image quality, learning the underlying factors of pose and appearance variation.

We propose to generate novel animations from a set of elementary examples of video-based surface motion capture, under user-specified constraints. 4D surface capture animation is motivated by the increasing demand from media production for highly realistic 3D content. To this aim, data driven strategies that consider video-based information can produce animation with real shapes, kinematics and appearances. Our animations rely on the combination and the interpolation of textured 3D mesh data, which requires examining two aspects: (1) Shape geometry and (2) appearance. First, we propose an animation synthesis structure for the shape geometry, the Essential graph, that outperforms standard Motion graphs in optimality with respect to quantitative criteria, and we extend optimized interpolated transition algorithms to mesh data. Second, we propose a compact view-independent representation for the shape appearance. This representation encodes subject appearance changes due to viewpoint and illumination, and due to inaccuracies in geometric modelling independently. Besides providing compact representations, such decompositions allow for additional applications such as interpolation for animation.

We address the problem of generating variations of captured 4D models automatically, and we particularly focus on dynamic human shapes as observed from multi-view videos. Variation is an essential component of motion realism, however recent mesh animation datasets and tools lack such richness. Given a few 4D models representing movements of the same type, our method builds a probabilistic low dimensional embedding of shape poses using Gaussian Process Dynamical Models, and novel variants of motions are obtained by sampling trajectories from this manifold using Monte Carlo Markov Chain. We can synthesise an unlimited number of variations of any of the input movements, and also any blended version of them, without costly non-linear interpolation of input movement variations in mesh domain. The output variations are statistically similar to the input movements but yet slightly different in poses and timings. As we show through our results, the generated mesh sequences match the training examples in realism, which facilitates 4D model dataset augmentation.

We address the problem of transferring motion between captured 4D models. We particularly focus on human subjects for which the ability to automatically augment 4D datasets, by propagating movements between subjects, is of interest in a great deal of recent vision applications that builds on human visual corpus. Given 4D training sets for two subjects for which a sparse set of corresponding keyposes are known, our method is able to transfer a newly captured motion from one subject to the other. With the aim to generalize transfers to input motions possibly very diverse with respect to the training sets, the method contributes with a new transfer model based on non-linear pose interpolation. Building on Gaussian process regression, this model intends to capture and preserve individual motion properties, and thereby realism, by accounting for pose inter-dependencies during motion transfers. Our experiments show visually qualitative, and quantitative, improvements over existing pose-mapping methods and confirm the generalization capabilities of our method compared to state of the art.

We propose a method to generate animations using video-based mesh sequences of elementary movements of a shape. New motions that satisfy high-level user-specified constraints are built by recombining and interpolating the frames in the observed mesh sequences. The interest of video based meshes is to provide real full shape information and to enable therefore realistic shape animations. A resulting issue lies, however, in the difficulty to combine and interpolate human poses without a parametric pose model, as with skeleton based animations. To address this issue, our method brings two innovations that contribute at different levels: Locally between two motion sequences, we introduce a new approach to generate realistic transitions using dynamic time warping, More globally, over a set of motion sequences, we propose the essential graph as an efficient structure to encode the most realistic transitions between all pairs of input shape poses. Graph search in the essential graph allows then to generate realistic motions that are optimal with respect to various user-defined constraints. We present both quantitative and qualitative results on various 3D video datasets. They show that our approach compares favourably with previous strategies in this field that use the motion graph.