Ko Nishino

Kohei Yamashita, Yuto Enyo, Shohei Nobuhara et al.

We introduce a novel multi-view stereo (MVS) method that can simultaneously recover not just per-pixel depth but also surface normals, together with the reflectance of textureless, complex non-Lambertian surfaces captured under known but natural illumination. Our key idea is to formulate MVS as an end-to-end learnable network, which we refer to as nLMVS-Net, that seamlessly integrates radiometric cues to leverage surface normals as view-independent surface features for learned cost volume construction and filtering. It first estimates surface normals as pixel-wise probability densities for each view with a novel shape-from-shading network. These per-pixel surface normal densities and the input multi-view images are then input to a novel cost volume filtering network that learns to recover per-pixel depth and surface normal. The reflectance is also explicitly estimated by alternating with geometry reconstruction. Extensive quantitative evaluations on newly established synthetic and real-world datasets show that nLMVS-Net can robustly and accurately recover the shape and reflectance of complex objects in natural settings.

Tomoki Ichikawa, Yoshiki Fukao, Shohei Nobuhara et al.

Computer vision applications have heavily relied on the linear combination of Lambertian diffuse and microfacet specular reflection models for representing reflected radiance, which turns out to be physically incompatible and limited in applicability. In this paper, we derive a novel analytical reflectance model, which we refer to as Fresnel Microfacet BRDF model, that is physically accurate and generalizes to various real-world surfaces. Our key idea is to model the Fresnel reflection and transmission of the surface microgeometry with a collection of oriented mirror facets, both for body and surface reflections. We carefully derive the Fresnel reflection and transmission for each microfacet as well as the light transport between them in the subsurface. This physically-grounded modeling also allows us to express the polarimetric behavior of reflected light in addition to its radiometric behavior. That is, FMBRDF unifies not only body and surface reflections but also light reflection in radiometry and polarization and represents them in a single model. Experimental results demonstrate its effectiveness in accuracy, expressive power, and image-based estimation.

Shu Nakamura, Yasutomo Kawanishi, Shohei Nobuhara et al.

In this paper, we realize automatic visual recognition and direction estimation of pointing. We introduce the first neural pointing understanding method based on two key contributions. The first is the introduction of a first-of-its-kind large-scale dataset for pointing recognition and direction estimation, which we refer to as the DP Dataset. DP Dataset consists of more than 2 million frames of 33 people pointing in various styles annotated for each frame with pointing timings and 3D directions. The second is DeePoint, a novel deep network model for joint recognition and 3D direction estimation of pointing. DeePoint is a Transformer-based network which fully leverages the spatio-temporal coordination of the body parts, not just the hands. Through extensive experiments, we demonstrate the accuracy and efficiency of DeePoint. We believe DP Dataset and DeePoint will serve as a sound foundation for visual human intention understanding.

Taichi Fukuda, Kotaro Hasegawa, Shinya Ishizaki et al.

We introduce 2D blind spot estimation as a critical visual task for road scene understanding. By automatically detecting road regions that are occluded from the vehicle's vantage point, we can proactively alert a manual driver or a self-driving system to potential causes of accidents (e.g., draw attention to a road region from which a child may spring out). Detecting blind spots in full 3D would be challenging, as 3D reasoning on the fly even if the car is equipped with LiDAR would be prohibitively expensive and error prone. We instead propose to learn to estimate blind spots in 2D, just from a monocular camera. We achieve this in two steps. We first introduce an automatic method for generating ``ground-truth'' blind spot training data for arbitrary driving videos by leveraging monocular depth estimation, semantic segmentation, and SLAM. The key idea is to reason in 3D but from 2D images by defining blind spots as those road regions that are currently invisible but become visible in the near future. We construct a large-scale dataset with this automatic offline blind spot estimation, which we refer to as Road Blind Spot (RBS) dataset. Next, we introduce BlindSpotNet (BSN), a simple network that fully leverages this dataset for fully automatic estimation of frame-wise blind spot probability maps for arbitrary driving videos. Extensive experimental results demonstrate the validity of our RBS Dataset and the effectiveness of our BSN.

Mai Nishimura, Shohei Nobuhara, Ko Nishino

We introduce a novel learning-based method for view birdification, the task of recovering ground-plane trajectories of pedestrians of a crowd and their observer in the same crowd just from the observed ego-centric video. View birdification becomes essential for mobile robot navigation and localization in dense crowds where the static background is hard to see and reliably track. It is challenging mainly for two reasons; i) absolute trajectories of pedestrians are entangled with the movement of the observer which needs to be decoupled from their observed relative movements in the ego-centric video, and ii) a crowd motion model describing the pedestrian movement interactions is specific to the scene yet unknown a priori. For this, we introduce a Transformer-based network referred to as ViewBirdiformer which implicitly models the crowd motion through self-attention and decomposes relative 2D movement observations onto the ground-plane trajectories of the crowd and the camera through cross-attention between views. Most important, ViewBirdiformer achieves view birdification in a single forward pass which opens the door to accurate real-time, always-on situational awareness. Extensive experimental results demonstrate that ViewBirdiformer achieves accuracy similar to or better than state-of-the-art with three orders of magnitude reduction in execution time.

Yuta Yoshitake, Mai Nishimura, Shohei Nobuhara et al.

We propose a novel method for joint estimation of shape and pose of rigid objects from their sequentially observed RGB-D images. In sharp contrast to past approaches that rely on complex non-linear optimization, we propose to formulate it as a neural optimization that learns to efficiently estimate the shape and pose. We introduce Deep Directional Distance Function (DeepDDF), a neural network that directly outputs the depth image of an object given the camera viewpoint and viewing direction, for efficient error computation in 2D image space. We formulate the joint estimation itself as a Transformer which we refer to as TransPoser. We fully leverage the tokenization and multi-head attention to sequentially process the growing set of observations and to efficiently update the shape and pose with a learned momentum, respectively. Experimental results on synthetic and real data show that DeepDDF achieves high accuracy as a category-level object shape representation and TransPoser achieves state-of-the-art accuracy efficiently for joint shape and pose estimation.

Yifan Zhan, Zhuoxiao Li, Muyao Niu et al.

We introduce KFD-NeRF, a novel dynamic neural radiance field integrated with an efficient and high-quality motion reconstruction framework based on Kalman filtering. Our key idea is to model the dynamic radiance field as a dynamic system whose temporally varying states are estimated based on two sources of knowledge: observations and predictions. We introduce a novel plug-in Kalman filter guided deformation field that enables accurate deformation estimation from scene observations and predictions. We use a shallow Multi-Layer Perceptron (MLP) for observations and model the motion as locally linear to calculate predictions with motion equations. To further enhance the performance of the observation MLP, we introduce regularization in the canonical space to facilitate the network's ability to learn warping for different frames. Additionally, we employ an efficient tri-plane representation for encoding the canonical space, which has been experimentally demonstrated to converge quickly with high quality. This enables us to use a shallower observation MLP, consisting of just two layers in our implementation. We conduct experiments on synthetic and real data and compare with past dynamic NeRF methods. Our KFD-NeRF demonstrates similar or even superior rendering performance within comparable computational time and achieves state-of-the-art view synthesis performance with thorough training.

Zhuoxiao Li, Zhihang Zhong, Shohei Nobuhara et al.

Polarization is a fundamental property of light that encodes abundant information regarding surface shape, material, illumination and viewing geometry. The computer vision community has witnessed a blossom of polarization-based vision applications, such as reflection removal, shape-from-polarization, transparent object segmentation and color constancy, partially due to the emergence of single-chip mono/color polarization sensors that make polarization data acquisition easier than ever. However, is polarization-based vision vulnerable to adversarial attacks? If so, is that possible to realize these adversarial attacks in the physical world, without being perceived by human eyes? In this paper, we warn the community of the vulnerability of polarization-based vision, which can be more serious than RGB-based vision. By adapting a commercial LCD projector, we achieve locally controllable polarizing projection, which is successfully utilized to fool state-of-the-art polarization-based vision algorithms for glass segmentation and color constancy. Compared with existing physical attacks on RGB-based vision, which always suffer from the trade-off between attack efficacy and eye conceivability, the adversarial attackers based on polarizing projection are contact-free and visually imperceptible, since naked human eyes can rarely perceive the difference of viciously manipulated polarizing light and ordinary illumination. This poses unprecedented risks on polarization-based vision, both in the monochromatic and trichromatic domain, for which due attentions should be paid and counter measures be considered.

Mai Nishimura, Shohei Nobuhara, Ko Nishino

We introduce an on-ground Pedestrian World Model, a computational model that can predict how pedestrians move around an observer in the crowd on the ground plane, but from just the egocentric-views of the observer. Our model, InCrowdFormer, fully leverages the Transformer architecture by modeling pedestrian interaction and egocentric to top-down view transformation with attention, and autoregressively predicts on-ground positions of a variable number of people with an encoder-decoder architecture. We encode the uncertainties arising from unknown pedestrian heights with latent codes to predict the posterior distributions of pedestrian positions. We validate the effectiveness of InCrowdFormer on a novel prediction benchmark of real movements. The results show that InCrowdFormer accurately predicts the future coordination of pedestrians. To the best of our knowledge, InCrowdFormer is the first-of-its-kind pedestrian world model which we believe will benefit a wide range of egocentric-view applications including crowd navigation, tracking, and synthesis.

Kohei Yamashita, Shohei Nobuhara, Ko Nishino

Geometry reconstruction of textureless, non-Lambertian objects under unknown natural illumination (i.e., in the wild) remains challenging as correspondences cannot be established and the reflectance cannot be expressed in simple analytical forms. We derive a novel multi-view method, DeepShaRM, that achieves state-of-the-art accuracy on this challenging task. Unlike past methods that formulate this as inverse-rendering, i.e., estimation of reflectance, illumination, and geometry from images, our key idea is to realize that reflectance and illumination need not be disentangled and instead estimated as a compound reflectance map. We introduce a novel deep reflectance map estimation network that recovers the camera-view reflectance maps from the surface normals of the current geometry estimate and the input multi-view images. The network also explicitly estimates per-pixel confidence scores to handle global light transport effects. A deep shape-from-shading network then updates the geometry estimate expressed with a signed distance function using the recovered reflectance maps. By alternating between these two, and, most important, by bypassing the ill-posed problem of reflectance and illumination decomposition, the method accurately recovers object geometry in these challenging settings. Extensive experiments on both synthetic and real-world data clearly demonstrate its state-of-the-art accuracy.

Shu Nakamura, Ryo Kawahara, Genki Kinoshita et al.

We introduce a novel 3D hand pose estimator that can accurately recover the shape and pose of people's hands in a room from afar, typically from fixed cameras at room corners, in extremely low-resolution and frequently occluded views. Our key idea is to fully leverage hand-body coordination, its temporal progression, and multiview observations. We achieve this with a novel Transformer-based model, in which hand and body configurations are modeled through correlations between their visual features expressed as per-view tokens, and their temporal coordination is exploited in an autoregressive manner. We introduce a novel dataset, which we refer to as REACH, Room-Environment dataset Annotated with Chest cameras for Hand pose estimation, to train and test our method. REACH is a first-of-its-kind large-scale hand pose dataset that captures accurate hand movements of 50 participants across a wide variety of daily activities. In order to avoid interfering with natural movements while annotating the hands with accurate shape and pose, we leverage concealed chest cameras. Through extensive experiments, including comparative studies with existing methods, we show that our model, REACH-Net, achieves highly accurate 3D hand pose estimation from afar. These results broaden the horizon of 3D hand pose estimation, especially towards "in-the-wild" continuous human behavior analysis.

Ryosuke Hirai, Kohei Yamashita, Antoine Guédon et al.

Reconstructing 3D geometry and appearance from a sparse set of fixed cameras is a foundational task with broad applications, yet it remains fundamentally constrained by the limited viewpoints. We show that this bound can be broken by exploiting opportunistic object motion: as a person manipulates an object~(e.g., moving a chair or lifting a mug), the static cameras effectively ``orbit'' the object in its local coordinate frame, providing additional virtual viewpoints. Harnessing this object motion, however, poses two challenges: the tight coupling of object pose and geometry estimation and the complex appearance variations of a moving object under static illumination. We address these by formulating a joint pose and shape optimization using 2D Gaussian splatting with alternating minimization of 6DoF trajectories and primitive parameters, and by introducing a novel appearance model that factorizes diffuse and specular components with reflected directional probing within the spherical harmonics space. Extensive experiments on synthetic and real-world datasets with extremely sparse viewpoints demonstrate that our method recovers significantly more accurate geometry and appearance than state-of-the-art baselines.

Nobuo Yoshii, Xinran Nicole Han, Ryo Kawahara et al.

We introduce Multi-Object Generative Perception (MultiGP), a generative inverse rendering method for stochastic sampling of all radiometric constituents -- reflectance, texture, and illumination -- underlying object appearance from a single image. Our key idea to solve this inherently ambiguous radiometric disentanglement is to leverage the fact that while their texture and reflectance may differ, objects in the same scene are all lit by the same illumination. MultiGP exploits this consensus to produce samples of reflectance, texture, and illumination from a single image of known shapes based on four key technical contributions: a cascaded end-to-end architecture that combines image-space and angular-space disentanglement; Coordinated Guidance for diffusion convergence to a single consistent illumination estimate; Axial Attention applied to facilitate ``cross-talk'' between objects of different reflectance; and a Texture Extraction ControlNet to preserve high-frequency texture details while ensuring decoupling from estimated lighting. Experimental results demonstrate that MultiGP effectively leverages the complementary spatial and frequency characteristics of multiple object appearances to recover individual texture and reflectance as well as the common illumination.

Norika Wada, Kohei Yamashita, Ryo Kawahara et al.

Knowledge of the physical material properties governing the dynamics of a real-world object becomes necessary to accurately anticipate its response to unseen interactions. Existing methods for estimating such physical material parameters from visual data assume homogeneous single-material objects, pre-learned dynamics, or simplistic topologies. Real-world objects, however, are often complex in material composition and geometry lying outside the realm of these assumptions. In this paper, we particularly focus on flowers as a representative common object. We introduce Multi-material Physical Gaussians (M-PhyGs) to estimate the material composition and parameters of such multi-material complex natural objects from video. From a short video captured in a natural setting, M-PhyGs jointly segments the object into similar materials and recovers their continuum mechanical parameters while accounting for gravity. M-PhyGs achieves this efficiently with newly introduced cascaded 3D and 2D losses, and by leveraging temporal mini-batching. We introduce a dataset, Phlowers, of people interacting with flowers as a novel platform to evaluate the accuracy of this challenging task of multi-material physical parameter estimation. Experimental results on Phlowers dataset demonstrate the accuracy and effectiveness of M-PhyGs and its components.

Akihiro Kubota, Tomoya Hasegawa, Ryo Kawahara et al.

Gauging an individual's skill level is crucial, as it inherently shapes their behavior. Quantifying skill, however, is challenging because it is latent to the observed actions. To explore skill understanding in human behavior, we focus on dyadic sports -- specifically table tennis -- where skill manifests not just in complex movements, but in the subtle nuances of execution conditioned on game context. Our key idea is to learn a generative model of each player's tactical racket strokes and jointly embed them in a common latent space that encodes individual characteristics, including those pertaining to skill levels. By training these player models on a large-scale dataset of 3D-reconstructed professional matches and conditioning them on comprehensive game context -- including player positioning and opponent behaviors -- the models capture individual tactical identities within their latent space. We probe this learned player space and find that it reflects distinct play styles and attributes that collectively represent skill. By training a simple relative ranking network on these embeddings, we demonstrate that both relative and absolute skill predictions can be achieved. These results demonstrate that the learned player space effectively quantifies skill levels, providing a foundation for automated skill assessment in complex, interactive behaviors.

Genki Kinoshita, Shu Nakamura, Ryo Kawahara et al.

Effective human behavior modeling requires a representation of the human body movement that capitalizes on its compositionality. We propose a hierarchical representation consisting of Action Atoms that capture the atomic joint movements and Action Motifs that are formed by their temporal compositions and encode similar body movements found across different overall human actions. We derive A4Mer, a nested latent Transformer to learn this hierarchical representation from human pose data in a fully self-supervised manner. A4Mer splits a 3D pose sequence into variable-length segments and represents each segment as a single latent token (Action Atoms). Through bottom-up representation learning, temporal patterns composed of these Action Atoms, which capture meaningful temporal spans of reusable, semantic segments of body movements, naturally emerge (Action Motifs). A4Mer achieves this with a unified pretext task of masked token prediction in their respective latent spaces. We also introduce Action Motif Dataset (AMD), a large-scale dataset of multi-view human behavior videos with full SMPL annotations. We introduce a novel use of cameras by mounting them on the feet to achieve their frame-wise annotations despite frequent and heavy body occlusions. Experimental results demonstrate the effectiveness of A4Mer for extracting meaningful Action Motifs, which significantly benefit human behavior modeling tasks including action recognition, motion prediction, and motion interpolation.

Antoine Guédon, Tomoki Ichikawa, Kohei Yamashita et al.

We present a novel appearance model that simultaneously realizes explicit high-quality 3D surface mesh recovery and photorealistic novel view synthesis from sparse view samples. Our key idea is to model the underlying scene geometry Mesh as an Atlas of Charts which we render with 2D Gaussian surfels (MAtCha Gaussians). MAtCha distills high-frequency scene surface details from an off-the-shelf monocular depth estimator and refines it through Gaussian surfel rendering. The Gaussian surfels are attached to the charts on the fly, satisfying photorealism of neural volumetric rendering and crisp geometry of a mesh model, i.e., two seemingly contradicting goals in a single model. At the core of MAtCha lies a novel neural deformation model and a structure loss that preserve the fine surface details distilled from learned monocular depths while addressing their fundamental scale ambiguities. Results of extensive experimental validation demonstrate MAtCha's state-of-the-art quality of surface reconstruction and photorealism on-par with top contenders but with dramatic reduction in the number of input views and computational time. We believe MAtCha will serve as a foundational tool for any visual application in vision, graphics, and robotics that require explicit geometry in addition to photorealism. Our project page is the following: https://anttwo.github.io/matcha/

Tomoki Ichikawa, Shohei Nobuhara, Ko Nishino

Can we capture shape and reflectance in stealth? Such capability would be valuable for many application domains in vision, xR, robotics, and HCI. We introduce structured polarization for invisible depth and reflectance sensing (SPIDeRS), the first depth and reflectance sensing method using patterns of polarized light. The key idea is to modulate the angle of linear polarization (AoLP) of projected light at each pixel. The use of polarization makes it invisible and lets us recover not only depth but also directly surface normals and even reflectance. We implement SPIDeRS with a liquid crystal spatial light modulator (SLM) and a polarimetric camera. We derive a novel method for robustly extracting the projected structured polarization pattern from the polarimetric object appearance. We evaluate the effectiveness of SPIDeRS by applying it to a number of real-world objects. The results show that our method successfully reconstructs object shapes of various materials and is robust to diffuse reflection and ambient light. We also demonstrate relighting using recovered surface normals and reflectance. We believe SPIDeRS opens a new avenue of polarization use in visual sensing.

Yuto Enyo, Ko Nishino

Reflectance bounds the frequency spectrum of illumination in the object appearance. In this paper, we introduce the first stochastic inverse rendering method, which recovers the attenuated frequency spectrum of an illumination jointly with the reflectance of an object of known geometry from a single image. Our key idea is to solve this blind inverse problem in the reflectance map, an appearance representation invariant to the underlying geometry, by learning to reverse the image formation with a novel diffusion model which we refer to as the Diffusion Reflectance Map Network (DRMNet). Given an observed reflectance map converted and completed from the single input image, DRMNet generates a reflectance map corresponding to a perfect mirror sphere while jointly estimating the reflectance. The forward process can be understood as gradually filtering a natural illumination with lower and lower frequency reflectance and additive Gaussian noise. DRMNet learns to invert this process with two subnetworks, IllNet and RefNet, which work in concert towards this joint estimation. The network is trained on an extensive synthetic dataset and is demonstrated to generalize to real images, showing state-of-the-art accuracy on established datasets.

Xinran Nicole Han, Todd Zickler, Ko Nishino

Models for inferring monocular shape of surfaces with diffuse reflection -- shape from shading -- ought to produce distributions of outputs, because there are fundamental mathematical ambiguities of both continuous (e.g., bas-relief) and discrete (e.g., convex/concave) types that are also experienced by humans. Yet, the outputs of current models are limited to point estimates or tight distributions around single modes, which prevent them from capturing these effects. We introduce a model that reconstructs a multimodal distribution of shapes from a single shading image, which aligns with the human experience of multistable perception. We train a small denoising diffusion process to generate surface normal fields from $16\times 16$ patches of synthetic images of everyday 3D objects. We deploy this model patch-wise at multiple scales, with guidance from inter-patch shape consistency constraints. Despite its relatively small parameter count and predominantly bottom-up structure, we show that multistable shape explanations emerge from this model for ambiguous test images that humans experience as being multistable. At the same time, the model produces veridical shape estimates for object-like images that include distinctive occluding contours and appear less ambiguous. This may inspire new architectures for stochastic 3D shape perception that are more efficient and better aligned with human experience.

Sang-Eun Lee, Ko Nishino, Shohei Nobuhara

We propose a novel method for spatiotemporal multi-camera calibration using freely moving people in multiview videos. Since calibrating multiple cameras and finding matches across their views are inherently interdependent, performing both in a unified framework poses a significant challenge. We address these issues as a single registration problem of matching two sets of 3D points, leveraging human motion in dynamic multi-person scenes. To this end, we utilize 3D human poses obtained from an off-the-shelf monocular 3D human pose estimator and transform them into 3D points on a unit sphere, to solve the rotation, time offset, and the association alternatingly. We employ a probabilistic approach that can jointly solve both problems of aligning spatiotemporal data and establishing correspondences through soft assignment between two views. The translation is determined by applying coplanarity constraints. The pairwise registration results are integrated into a multiview setup, and then a nonlinear optimization method is used to improve the accuracy of the camera poses, temporal offsets, and multi-person associations. Extensive experiments on synthetic and real data demonstrate the effectiveness and flexibility of the proposed method as a practical marker-free calibration tool.

Shota Sasaki, Jane Wu, Ko Nishino

This paper introduces a novel clothed human model that can be learned from multiview RGB videos, with a particular emphasis on recovering physically accurate body and cloth movements. Our method, Position Based Dynamic Gaussians (PBDyG), realizes ``movement-dependent'' cloth deformation via physical simulation, rather than merely relying on ``pose-dependent'' rigid transformations. We model the clothed human holistically but with two distinct physical entities in contact: clothing modeled as 3D Gaussians, which are attached to a skinned SMPL body that follows the movement of the person in the input videos. The articulation of the SMPL body also drives physically-based simulation of the clothes' Gaussians to transform the avatar to novel poses. In order to run position based dynamics simulation, physical properties including mass and material stiffness are estimated from the RGB videos through Dynamic 3D Gaussian Splatting. Experiments demonstrate that our method not only accurately reproduces appearance but also enables the reconstruction of avatars wearing highly deformable garments, such as skirts or coats, which have been challenging to reconstruct using existing methods.

Genki Kinoshita, Ko Nishino

In this paper, we introduce a novel training method for making any monocular depth network learn absolute scale and estimate metric road-scene depth just from regular training data, i.e., driving videos. We refer to this training framework as FUMET. The key idea is to leverage cars found on the road as sources of scale supervision and to incorporate them in network training robustly. FUMET detects and estimates the sizes of cars in a frame and aggregates scale information extracted from them into an estimate of the camera height whose consistency across the entire video sequence is enforced as scale supervision. This realizes robust unsupervised training of any, otherwise scale-oblivious, monocular depth network so that they become not only scale-aware but also metric-accurate without the need for auxiliary sensors and extra supervision. Extensive experiments on the KITTI and the Cityscapes datasets show the effectiveness of FUMET, which achieves state-of-the-art accuracy. We also show that FUMET enables training on mixed datasets of different camera heights, which leads to larger-scale training and better generalization. Metric depth reconstruction is essential in any road-scene visual modeling, and FUMET democratizes its deployment by establishing the means to convert any model into a metric depth estimator.

Xinran Nicole Han, Ko Nishino, Todd Zickler

Perceiving the shape and material of an object from a single image is inherently ambiguous, especially when lighting is unknown and unconstrained. Despite this, humans can often disentangle shape and material, and when they are uncertain, they often move their head slightly or rotate the object to help resolve the ambiguities. Inspired by this behavior, we introduce a novel conditional denoising-diffusion model that generates samples of shape-and-material maps from a short video of an object undergoing differential motions. Our parameter-efficient architecture allows training directly in pixel-space, and it generates many disentangled attributes of an object simultaneously. Trained on a modest number of synthetic object-motion videos with supervision on shape and material, the model exhibits compelling emergent behavior: For static observations, it produces diverse, multimodal predictions of plausible shape-and-material maps that capture the inherent ambiguities; and when objects move, the distributions converge to more accurate explanations. The model also produces high-quality shape-and-material estimates for less ambiguous, real-world objects. By moving beyond single-view to continuous motion observations, and by using generative perception to capture visual ambiguities, our work suggests ways to improve visual reasoning in physically-embodied systems.

Sang-Eun Lee, Ko Nishino, Shohei Nobuhara

Can freely moving humans or animals themselves serve as calibration targets for multi-camera systems while simultaneously estimating their correspondences across views? We humans can solve this problem by mentally rotating the observed 2D poses and aligning them with those in the target views. Inspired by this cognitive ability, we propose SteerPose, a neural network that performs this rotation of 2D poses into another view. By integrating differentiable matching, SteerPose simultaneously performs extrinsic camera calibration and correspondence search within a single unified framework. We also introduce a novel geometric consistency loss that explicitly ensures that the estimated rotation and correspondences result in a valid translation estimation. Experimental results on diverse in-the-wild datasets of humans and animals validate the effectiveness and robustness of the proposed method. Furthermore, we demonstrate that our method can reconstruct the 3D poses of novel animals in multi-camera setups by leveraging off-the-shelf 2D pose estimators and our class-agnostic model.

Tomoki Ichikawa, Ryo Kawahara, Ko Nishino

We propose spatial polarization multiplexing (SPM) for reconstructing object shape and reflectance from a single polarimetric image and demonstrate its application to dynamic surface recovery. Although single-pattern structured light enables single-shot shape reconstruction, the reflectance is challenging to recover due to the lack of angular sampling of incident light and the entanglement of the projected pattern and the surface color texture. We design a spatially multiplexed pattern of polarization that can be robustly and uniquely decoded for shape reconstruction by quantizing the AoLP values. At the same time, our spatial-multiplexing enables single-shot ellipsometry of linear polarization by projecting differently polarized light within a local region, which separates the specular and diffuse reflections for BRDF estimation. We achieve this spatial polarization multiplexing with a constrained de Bruijn sequence. Unlike single-pattern structured light with intensity and color, our polarization pattern is invisible to the naked eye and retains the natural surface appearance which is essential for accurate appearance modeling and also interaction with people. We experimentally validate our method on real data. The results show that our method can recover the shape, the Mueller matrix, and the BRDF from a single-shot polarimetric image. We also demonstrate the application of our method to dynamic surfaces.

Liam Schoneveld, Zhe Chen, Davide Davoli et al.

Accurate, real-time 3D reconstruction of human heads from monocular images and videos underlies numerous visual applications. As 3D ground truth data is hard to come by at scale, previous methods have sought to learn from abundant 2D videos in a self-supervised manner. Typically, this involves the use of differentiable mesh rendering, which is effective but faces limitations. To improve on this, we propose SHeaP (Self-supervised Head Geometry Predictor Learned via 2D Gaussians). Given a source image, we predict a 3DMM mesh and a set of Gaussians that are rigged to this mesh. We then reanimate this rigged head avatar to match a target frame, and backpropagate photometric losses to both the 3DMM and Gaussian prediction networks. We find that using Gaussians for rendering substantially improves the effectiveness of this self-supervised approach. Training solely on 2D data, our method surpasses existing self-supervised approaches in geometric evaluations on the NoW benchmark for neutral faces and a new benchmark for non-neutral expressions. Our method also produces highly expressive meshes, outperforming state-of-the-art in emotion classification.

Ayaka Higami, Karin Oshima, Tomoyo Isoguchi Shiramatsu et al.

Analyzing rat behavior lies at the heart of many scientific studies. Past methods for automated rodent modeling have focused on 3D pose estimation from keypoints, e.g., face and appendages. The pose, however, does not capture the rich body surface movement encoding the subtle rat behaviors like curling and stretching. The body surface lacks features that can be visually defined, evading these established keypoint-based methods. In this paper, we introduce the first method for reconstructing the rat body surface as a dense set of points by learning to predict it from the sparse keypoints that can be detected with past methods. Our method consists of two key contributions. The first is RatDome, a novel multi-camera system for rat behavior capture, and a large-scale dataset captured with it that consists of pairs of 3D keypoints and 3D body surface points. The second is RatBodyFormer, a novel network to transform detected keypoints to 3D body surface points. RatBodyFormer is agnostic to the exact locations of the 3D body surface points in the training data and is trained with masked-learning. We experimentally validate our framework with a number of real-world experiments. Our results collectively serve as a novel foundation for automated rat behavior analysis.

Yuto Matsubara, Ko Nishino

We introduce a novel method for human shape and pose recovery that can fully leverage multiple static views. We target fixed-multiview people monitoring, including elderly care and safety monitoring, in which calibrated cameras can be installed at the corners of a room or an open space but whose configuration may vary depending on the environment. Our key idea is to formulate it as neural optimization. We achieve this with HeatFormer, a neural optimizer that iteratively refines the SMPL parameters given multiview images, which is fundamentally agonistic to the configuration of views. HeatFormer realizes this SMPL parameter estimation as heat map generation and alignment with a novel transformer encoder and decoder. We demonstrate the effectiveness of HeatFormer including its accuracy, robustness to occlusion, and generalizability through an extensive set of experiments. We believe HeatFormer can serve a key role in passive human behavior modeling.

Kohei Yamashita, Vincent Lepetit, Ko Nishino

Computer vision has long relied on two kinds of correspondences: pixel correspondences in images and 3D correspondences on object surfaces. Is there another kind, and if there is, what can they do for us? In this paper, we introduce correspondences of the third kind we call reflection correspondences and show that they can help estimate camera pose by just looking at objects without relying on the background. Reflection correspondences are point correspondences in the reflected world, i.e., the scene reflected by the object surface. The object geometry and reflectance alters the scene geometrically and radiometrically, respectively, causing incorrect pixel correspondences. Geometry recovered from each image is also hampered by distortions, namely generalized bas-relief ambiguity, leading to erroneous 3D correspondences. We show that reflection correspondences can resolve the ambiguities arising from these distortions. We introduce a neural correspondence estimator and a RANSAC algorithm that fully leverages all three kinds of correspondences for robust and accurate joint camera pose and object shape estimation just from the object appearance. The method expands the horizon of numerous downstream tasks, including camera pose estimation for appearance modeling (e.g., NeRF) and motion estimation of reflective objects (e.g., cars on the road), to name a few, as it relieves the requirement of overlapping background.

Mai Nishimura, Shohei Nobuhara, Ko Nishino

We introduce view birdification, the problem of recovering ground-plane movements of people in a crowd from an ego-centric video captured from an observer (e.g., a person or a vehicle) also moving in the crowd. Recovered ground-plane movements would provide a sound basis for situational understanding and benefit downstream applications in computer vision and robotics. In this paper, we formulate view birdification as a geometric trajectory reconstruction problem and derive a cascaded optimization method from a Bayesian perspective. The method first estimates the observer's movement and then localizes surrounding pedestrians for each frame while taking into account the local interactions between them. We introduce three datasets by leveraging synthetic and real trajectories of people in crowds and evaluate the effectiveness of our method. The results demonstrate the accuracy of our method and set the ground for further studies of view birdification as an important but challenging visual understanding problem.

Jia Xue, Hang Zhang, Ko Nishino et al.

Computational surface modeling that underlies material recognition has transitioned from reflectance modeling using in-lab controlled radiometric measurements to image-based representations based on internet-mined single-view images captured in the scene. We take a middle-ground approach for material recognition that takes advantage of both rich radiometric cues and flexible image capture. A key concept is differential angular imaging, where small angular variations in image capture enables angular-gradient features for an enhanced appearance representation that improves recognition. We build a large-scale material database, Ground Terrain in Outdoor Scenes (GTOS) database, to support ground terrain recognition for applications such as autonomous driving and robot navigation. The database consists of over 30,000 images covering 40 classes of outdoor ground terrain under varying weather and lighting conditions. We develop a novel approach for material recognition called texture-encoded angular network (TEAN) that combines deep encoding pooling of RGB information and differential angular images for angular-gradient features to fully leverage this large dataset. With this novel network architecture, we extract characteristics of materials encoded in the angular and spatial gradients of their appearance. Our results show that TEAN achieves recognition performance that surpasses single view performance and standard (non-differential/large-angle sampling) multiview performance.

Yuzheng Xu, Yang Wu, Nur Sabrina binti Zuraimi et al.

Video analysis has been moving towards more detailed interpretation (e.g. segmentation) with encouraging progresses. These tasks, however, increasingly rely on densely annotated training data both in space and time. Since such annotation is labour-intensive, few densely annotated video data with detailed region boundaries exist. This work aims to resolve this dilemma by learning to automatically generate region boundaries for all frames of a video from sparsely annotated bounding boxes of target regions. We achieve this with a Volumetric Graph Convolutional Network (VGCN), which learns to iteratively find keypoints on the region boundaries using the spatio-temporal volume of surrounding appearance and motion. The global optimization of VGCN makes it significantly stronger and generalize better than existing solutions. Experimental results using two latest datasets (one real and one synthetic), including ablation studies, demonstrate the effectiveness and superiority of our method.

Zhe Chen, Shohei Nobuhara, Ko Nishino

We introduce a novel neural network-based BRDF model and a Bayesian framework for object inverse rendering, i.e., joint estimation of reflectance and natural illumination from a single image of an object of known geometry. The BRDF is expressed with an invertible neural network, namely, normalizing flow, which provides the expressive power of a high-dimensional representation, computational simplicity of a compact analytical model, and physical plausibility of a real-world BRDF. We extract the latent space of real-world reflectance by conditioning this model, which directly results in a strong reflectance prior. We refer to this model as the invertible neural BRDF model (iBRDF). We also devise a deep illumination prior by leveraging the structural bias of deep neural networks. By integrating this novel BRDF model and reflectance and illumination priors in a MAP estimation formulation, we show that this joint estimation can be computed efficiently with stochastic gradient descent. We experimentally validate the accuracy of the invertible neural BRDF model on a large number of measured data and demonstrate its use in object inverse rendering on a number of synthetic and real images. The results show new ways in which deep neural networks can help solve challenging radiometric inverse problems.

Kohei Yamashita, Shohei Nobuhara, Ko Nishino

In this paper, we introduce 3D-GMNet, a deep neural network for 3D object shape reconstruction from a single image. As the name suggests, 3D-GMNet recovers 3D shape as a Gaussian mixture. In contrast to voxels, point clouds, or meshes, a Gaussian mixture representation provides an analytical expression with a small memory footprint while accurately representing the target 3D shape. At the same time, it offers a number of additional advantages including instant pose estimation and controllable level-of-detail reconstruction, while also enabling interpretation as a point cloud, volume, and a mesh model. We train 3D-GMNet end-to-end with single input images and corresponding 3D models by introducing two novel loss functions, a 3D Gaussian mixture loss and a 2D multi-view loss, which collectively enable accurate shape reconstruction as kernel density estimation. We thoroughly evaluate the effectiveness of 3D-GMNet with synthetic and real images of objects. The results show accurate reconstruction with a compact representation that also realizes novel applications of single-image 3D reconstruction.

Ryo Kawahara, Meng-Yu Jennifer Kuo, Shohei Nobuhara et al.

This paper introduces single-image geometric and appearance reconstruction from water reflection photography, i.e., images capturing direct and water-reflected real-world scenes. Water reflection offers an additional viewpoint to the direct sight, collectively forming a stereo pair. The water-reflected scene, however, includes internally scattered and reflected environmental illumination in addition to the scene radiance, which precludes direct stereo matching. We derive a principled iterative method that disentangles this scene radiometry and geometry for reconstructing 3D scene structure as well as its high-dynamic range appearance. In the presence of waves, we simultaneously recover the wave geometry as surface normal perturbations of the water surface. Most important, we show that the water reflection enables calibration of the camera. In other words, for the first time, we show that capturing a direct and water-reflected scene in a single exposure forms a self-calibrating HDR catadioptric stereo camera. We demonstrate our method on a number of images taken in the wild. The results demonstrate a new means for leveraging this accidental catadioptric camera.

Gabriel Schwartz, Ko Nishino

Humans rely on properties of the materials that make up objects to guide our interactions with them. Grasping smooth materials, for example, requires care, and softness is an ideal property for fabric used in bedding. Even when these properties are not visual (e.g. softness is a physical property), we may still infer their presence visually. We refer to such material properties as visual material attributes. Recognizing these attributes in images can contribute valuable information for general scene understanding and material recognition. Unlike well-known object and scene attributes, visual material attributes are local properties with no fixed shape or spatial extent. We show that given a set of images annotated with known material attributes, we may accurately recognize the attributes from small local image patches. Obtaining such annotations in a consistent fashion at scale, however, is challenging. To address this, we introduce a method that allows us to probe the human visual perception of materials by asking simple yes/no questions comparing pairs of image patches. This provides sufficient weak supervision to build a set of attributes and associated classifiers that, while unnamed, serve the same function as the named attributes we use to describe materials. Doing so allows us to recognize visual material attributes without resorting to exhaustive manual annotation of a fixed set of named attributes. Furthermore, we show that this method may be integrated in the end-to-end learning of a material classification CNN to simultaneously recognize materials and discover their visual attributes. Our experimental results show that visual material attributes, whether named or automatically discovered, provide a useful intermediate representation for known material categories themselves as well as a basis for transfer learning when recognizing previously-unseen categories.

Jia Xue, Hang Zhang, Kristin Dana et al.

Material recognition for real-world outdoor surfaces has become increasingly important for computer vision to support its operation "in the wild." Computational surface modeling that underlies material recognition has transitioned from reflectance modeling using in-lab controlled radiometric measurements to image-based representations based on internet-mined images of materials captured in the scene. We propose to take a middle-ground approach for material recognition that takes advantage of both rich radiometric cues and flexible image capture. We realize this by developing a framework for differential angular imaging, where small angular variations in image capture provide an enhanced appearance representation and significant recognition improvement. We build a large-scale material database, Ground Terrain in Outdoor Scenes (GTOS) database, geared towards real use for autonomous agents. The database consists of over 30,000 images covering 40 classes of outdoor ground terrain under varying weather and lighting conditions. We develop a novel approach for material recognition called a Differential Angular Imaging Network (DAIN) to fully leverage this large dataset. With this novel network architecture, we extract characteristics of materials encoded in the angular and spatial gradients of their appearance. Our results show that DAIN achieves recognition performance that surpasses single view or coarsely quantized multiview images. These results demonstrate the effectiveness of differential angular imaging as a means for flexible, in-place material recognition.

Gabriel Schwartz, Ko Nishino

Recognition of materials has proven to be a challenging problem due to the wide variation in appearance within and between categories. Global image context, such as where the material is or what object it makes up, can be crucial to recognizing the material. Existing methods, however, operate on an implicit fusion of materials and context by using large receptive fields as input (i.e., large image patches). Many recent material recognition methods treat materials as yet another set of labels like objects. Materials are, however, fundamentally different from objects as they have no inherent shape or defined spatial extent. Approaches that ignore this can only take advantage of limited implicit context as it appears during training. We instead show that recognizing materials purely from their local appearance and integrating separately recognized global contextual cues including objects and places leads to superior dense, per-pixel, material recognition. We achieve this by training a fully-convolutional material recognition network end-to-end with only material category supervision. We integrate object and place estimates to this network from independent CNNs. This approach avoids the necessity of preparing an impractically-large amount of training data to cover the product space of materials, objects, and scenes, while fully leveraging contextual cues for dense material recognition. Furthermore, we perform a detailed analysis of the effects of context granularity, spatial resolution, and the network level at which we introduce context. On a recently introduced comprehensive and diverse material database \cite{Schwartz2016}, we confirm that our method achieves state-of-the-art accuracy with significantly less training data compared to past methods.

Stephen Lombardi, Ko Nishino

Recovering the radiometric properties of a scene (i.e., the reflectance, illumination, and geometry) is a long-sought ability of computer vision that can provide invaluable information for a wide range of applications. Deciphering the radiometric ingredients from the appearance of a real-world scene, as opposed to a single isolated object, is particularly challenging as it generally consists of various objects with different material compositions exhibiting complex reflectance and light interactions that are also part of the illumination. We introduce the first method for radiometric scene decomposition that handles those intricacies. We use RGB-D images to bootstrap geometry recovery and simultaneously recover the complex reflectance and natural illumination while refining the noisy initial geometry and segmenting the scene into different material regions. Most important, we handle real-world scenes consisting of multiple objects of unknown materials, which necessitates the modeling of spatially-varying complex reflectance, natural illumination, texture, interreflection and shadows. We systematically evaluate the effectiveness of our method on synthetic scenes and demonstrate its application to real-world scenes. The results show that rich radiometric information can be recovered from RGB-D images and demonstrate a new role RGB-D sensors can play for general scene understanding tasks.

Gabriel Schwartz, Ko Nishino

Material attributes have been shown to provide a discriminative intermediate representation for recognizing materials, especially for the challenging task of recognition from local material appearance (i.e., regardless of object and scene context). In the past, however, material attributes have been recognized separately preceding category recognition. In contrast, neuroscience studies on material perception and computer vision research on object and place recognition have shown that attributes are produced as a by-product during the category recognition process. Does the same hold true for material attribute and category recognition? In this paper, we introduce a novel material category recognition network architecture to show that perceptual attributes can, in fact, be automatically discovered inside a local material recognition framework. The novel material-attribute-category convolutional neural network (MAC-CNN) produces perceptual material attributes from the intermediate pooling layers of an end-to-end trained category recognition network using an auxiliary loss function that encodes human material perception. To train this model, we introduce a novel large-scale database of local material appearance organized under a canonical material category taxonomy and careful image patch extraction that avoids unwanted object and scene context. We show that the discovered attributes correspond well with semantically-meaningful visual material traits via Boolean algebra, and enable recognition of previously unseen material categories given only a few examples. These results have strong implications in how perceptually meaningful attributes can be learned in other recognition tasks.

Hang Zhang, Kristin Dana, Ko Nishino

Images are the standard input for vision algorithms, but one-shot infield reflectance measurements are creating new opportunities for recognition and scene understanding. In this work, we address the question of what reflectance can reveal about materials in an efficient manner. We go beyond the question of recognition and labeling and ask the question: What intrinsic physical properties of the surface can be estimated using reflectance? We introduce a framework that enables prediction of actual friction values for surfaces using one-shot reflectance measurements. This work is a first of its kind vision-based friction estimation. We develop a novel representation for reflectance disks that capture partial BRDF measurements instantaneously. Our method of deep reflectance codes combines CNN features and fisher vector pooling with optimal binary embedding to create codes that have sufficient discriminatory power and have important properties of illumination and spatial invariance. The experimental results demonstrate that reflectance can play a new role in deciphering the underlying physical properties of real-world scenes.

Hang Zhang, Kristin Dana, Ko Nishino

We introduce a novel method for using reflectance to identify materials. Reflectance offers a unique signature of the material but is challenging to measure and use for recognizing materials due to its high-dimensionality. In this work, one-shot reflectance is captured using a unique optical camera measuring {\it reflectance disks} where the pixel coordinates correspond to surface viewing angles. The reflectance has class-specific stucture and angular gradients computed in this reflectance space reveal the material class. These reflectance disks encode discriminative information for efficient and accurate material recognition. We introduce a framework called reflectance hashing that models the reflectance disks with dictionary learning and binary hashing. We demonstrate the effectiveness of reflectance hashing for material recognition with a number of real-world materials.