Yifan Wang

Yufeng Zheng, Wang Yifan, Gordon Wetzstein et al. · stanford

The ability to create realistic, animatable and relightable head avatars from casual video sequences would open up wide ranging applications in communication and entertainment. Current methods either build on explicit 3D morphable meshes (3DMM) or exploit neural implicit representations. The former are limited by fixed topology, while the latter are non-trivial to deform and inefficient to render. Furthermore, existing approaches entangle lighting in the color estimation, thus they are limited in re-rendering the avatar in new environments. In contrast, we propose PointAvatar, a deformable point-based representation that disentangles the source color into intrinsic albedo and normal-dependent shading. We demonstrate that PointAvatar bridges the gap between existing mesh- and implicit representations, combining high-quality geometry and appearance with topological flexibility, ease of deformation and rendering efficiency. We show that our method is able to generate animatable 3D avatars using monocular videos from multiple sources including hand-held smartphones, laptop webcams and internet videos, achieving state-of-the-art quality in challenging cases where previous methods fail, e.g., thin hair strands, while being significantly more efficient in training than competing methods.

Alexander W. Bergman, Petr Kellnhofer, Wang Yifan et al. · stanford

Unsupervised learning of 3D-aware generative adversarial networks (GANs) using only collections of single-view 2D photographs has very recently made much progress. These 3D GANs, however, have not been demonstrated for human bodies and the generated radiance fields of existing frameworks are not directly editable, limiting their applicability in downstream tasks. We propose a solution to these challenges by developing a 3D GAN framework that learns to generate radiance fields of human bodies or faces in a canonical pose and warp them using an explicit deformation field into a desired body pose or facial expression. Using our framework, we demonstrate the first high-quality radiance field generation results for human bodies. Moreover, we show that our deformation-aware training procedure significantly improves the quality of generated bodies or faces when editing their poses or facial expressions compared to a 3D GAN that is not trained with explicit deformations.

Xingyi He, Jiaming Sun, Yifan Wang et al. · stanford

We propose a new structure-from-motion framework to recover accurate camera poses and point clouds from unordered images. Traditional SfM systems typically rely on the successful detection of repeatable keypoints across multiple views as the first step, which is difficult for texture-poor scenes, and poor keypoint detection may break down the whole SfM system. We propose a new detector-free SfM framework to draw benefits from the recent success of detector-free matchers to avoid the early determination of keypoints, while solving the multi-view inconsistency issue of detector-free matchers. Specifically, our framework first reconstructs a coarse SfM model from quantized detector-free matches. Then, it refines the model by a novel iterative refinement pipeline, which iterates between an attention-based multi-view matching module to refine feature tracks and a geometry refinement module to improve the reconstruction accuracy. Experiments demonstrate that the proposed framework outperforms existing detector-based SfM systems on common benchmark datasets. We also collect a texture-poor SfM dataset to demonstrate the capability of our framework to reconstruct texture-poor scenes. Based on this framework, we take $\textit{first place}$ in Image Matching Challenge 2023.

Boyang Deng, Yifan Wang, Gordon Wetzstein · stanford

Unsupervised learning of 3D human faces from unstructured 2D image data is an active research area. While recent works have achieved an impressive level of photorealism, they commonly lack control of lighting, which prevents the generated assets from being deployed in novel environments. To this end, we introduce LumiGAN, an unconditional Generative Adversarial Network (GAN) for 3D human faces with a physically based lighting module that enables relighting under novel illumination at inference time. Unlike prior work, LumiGAN can create realistic shadow effects using an efficient visibility formulation that is learned in a self-supervised manner. LumiGAN generates plausible physical properties for relightable faces, including surface normals, diffuse albedo, and specular tint without any ground truth data. In addition to relightability, we demonstrate significantly improved geometry generation compared to state-of-the-art non-relightable 3D GANs and notably better photorealism than existing relightable GANs.

Wei-Ting Chen, Wang Yifan, Sy-Yen Kuo et al.

Neural radiance fields (NeRFs) have demonstrated state-of-the-art performance for 3D computer vision tasks, including novel view synthesis and 3D shape reconstruction. However, these methods fail in adverse weather conditions. To address this challenge, we introduce DehazeNeRF as a framework that robustly operates in hazy conditions. DehazeNeRF extends the volume rendering equation by adding physically realistic terms that model atmospheric scattering. By parameterizing these terms using suitable networks that match the physical properties, we introduce effective inductive biases, which, together with the proposed regularizations, allow DehazeNeRF to demonstrate successful multi-view haze removal, novel view synthesis, and 3D shape reconstruction where existing approaches fail.

Yifan Wang, Yi Gong, Yuan Zeng

Recent advances in Neural radiance fields (NeRF) have enabled high-fidelity scene reconstruction for novel view synthesis. However, NeRF requires hundreds of network evaluations per pixel to approximate a volume rendering integral, making it slow to train. Caching NeRFs into explicit data structures can effectively enhance rendering speed but at the cost of higher memory usage. To address these issues, we present Hyb-NeRF, a novel neural radiance field with a multi-resolution hybrid encoding that achieves efficient neural modeling and fast rendering, which also allows for high-quality novel view synthesis. The key idea of Hyb-NeRF is to represent the scene using different encoding strategies from coarse-to-fine resolution levels. Hyb-NeRF exploits memory-efficiency learnable positional features at coarse resolutions and the fast optimization speed and local details of hash-based feature grids at fine resolutions. In addition, to further boost performance, we embed cone tracing-based features in our learnable positional encoding that eliminates encoding ambiguity and reduces aliasing artifacts. Extensive experiments on both synthetic and real-world datasets show that Hyb-NeRF achieves faster rendering speed with better rending quality and even a lower memory footprint in comparison to previous state-of-the-art methods.

Junwen He, Yifan Wang, Lijun Wang et al.

Multimodal Large Language Model (MLLMs) leverages Large Language Models as a cognitive framework for diverse visual-language tasks. Recent efforts have been made to equip MLLMs with visual perceiving and grounding capabilities. However, there still remains a gap in providing fine-grained pixel-level perceptions and extending interactions beyond text-specific inputs. In this work, we propose {\bf{AnyRef}}, a general MLLM model that can generate pixel-wise object perceptions and natural language descriptions from multi-modality references, such as texts, boxes, images, or audio. This innovation empowers users with greater flexibility to engage with the model beyond textual and regional prompts, without modality-specific designs. Through our proposed refocusing mechanism, the generated grounding output is guided to better focus on the referenced object, implicitly incorporating additional pixel-level supervision. This simple modification utilizes attention scores generated during the inference of LLM, eliminating the need for extra computations while exhibiting performance enhancements in both grounding masks and referring expressions. With only publicly available training data, our model achieves state-of-the-art results across multiple benchmarks, including diverse modality referring segmentation and region-level referring expression generation.

Yifan Wang, Peishan Yang, Zhen Xu et al.

This paper addresses the challenge of reconstructing dynamic 3D scenes with complex motions. Some recent works define 3D Gaussian primitives in the canonical space and use deformation fields to map canonical primitives to observation spaces, achieving real-time dynamic view synthesis. However, these methods often struggle to handle scenes with complex motions due to the difficulty of optimizing deformation fields. To overcome this problem, we propose FreeTimeGS, a novel 4D representation that allows Gaussian primitives to appear at arbitrary time and locations. In contrast to canonical Gaussian primitives, our representation possesses the strong flexibility, thus improving the ability to model dynamic 3D scenes. In addition, we endow each Gaussian primitive with an motion function, allowing it to move to neighboring regions over time, which reduces the temporal redundancy. Experiments results on several datasets show that the rendering quality of our method outperforms recent methods by a large margin. Project page: https://zju3dv.github.io/freetimegs/ .

Shuyin Xia, Bolun Shi, Yifan Wang et al.

Traditional clustering algorithms often focus on the most fine-grained information and achieve clustering by calculating the distance between each pair of data points or implementing other calculations based on points. This way is not inconsistent with the cognitive mechanism of "global precedence" in human brain, resulting in those methods' bad performance in efficiency, generalization ability and robustness. To address this problem, we propose a new clustering algorithm called granular-ball clustering (GBCT) via granular-ball computing. Firstly, GBCT generates a smaller number of granular-balls to represent the original data, and forms clusters according to the relationship between granular-balls, instead of the traditional point relationship. At the same time, its coarse-grained characteristics are not susceptible to noise, and the algorithm is efficient and robust; besides, as granular-balls can fit various complex data, GBCT performs much better in non-spherical data sets than other traditional clustering methods. The completely new coarse granularity representation method of GBCT and cluster formation mode can also used to improve other traditional methods.

Zaibin Zhang, Yuanhang Zhang, Lijun Wang et al.

A popular approach for constructing bird's-eye-view (BEV) representation in 3D detection is to lift 2D image features onto the viewing frustum space based on explicitly predicted depth distribution. However, depth distribution can only characterize the 3D geometry of visible object surfaces but fails to capture their internal space and overall geometric structure, leading to sparse and unsatisfactory 3D representations. To mitigate this issue, we present BEV-IO, a new 3D detection paradigm to enhance BEV representation with instance occupancy information. At the core of our method is the newly-designed instance occupancy prediction (IOP) module, which aims to infer point-level occupancy status for each instance in the frustum space. To ensure training efficiency while maintaining representational flexibility, it is trained using the combination of both explicit and implicit supervision. With the predicted occupancy, we further design a geometry-aware feature propagation mechanism (GFP), which performs self-attention based on occupancy distribution along each ray in frustum and is able to enforce instance-level feature consistency. By integrating the IOP module with GFP mechanism, our BEV-IO detector is able to render highly informative 3D scene structures with more comprehensive BEV representations. Experimental results demonstrate that BEV-IO can outperform state-of-the-art methods while only adding a negligible increase in parameters (0.2%) and computational overhead (0.24%in GFLOPs).

Wang Yifan, Carl Doersch, Relja Arandjelović et al.

Much of the recent progress in 3D vision has been driven by the development of specialized architectures that incorporate geometrical inductive biases. In this paper we tackle 3D reconstruction using a domain agnostic architecture and study how instead to inject the same type of inductive biases directly as extra inputs to the model. This approach makes it possible to apply existing general models, such as Perceivers, on this rich domain, without the need for architectural changes, while simultaneously maintaining data efficiency of bespoke models. In particular we study how to encode cameras, projective ray incidence and epipolar geometry as model inputs, and demonstrate competitive multi-view depth estimation performance on multiple benchmarks.

Yifan Wang, Linjie Luo, Xiaohui Shen et al.

Recently, significant progress has been made in single-view depth estimation thanks to increasingly large and diverse depth datasets. However, these datasets are largely limited to specific application domains (e.g. indoor, autonomous driving) or static in-the-wild scenes due to hardware constraints or technical limitations of 3D reconstruction. In this paper, we introduce the first depth dataset DynOcc consisting of dynamic in-the-wild scenes. Our approach leverages the occlusion cues in these dynamic scenes to infer depth relationships between points of selected video frames. To achieve accurate occlusion detection and depth order estimation, we employ a novel occlusion boundary detection, filtering and thinning scheme followed by a robust foreground/background classification method. In total our DynOcc dataset contains 22M depth pairs out of 91K frames from a diverse set of videos. Using our dataset we achieved state-of-the-art results measured in weighted human disagreement rate (WHDR). We also show that the inferred depth maps trained with DynOcc can preserve sharper depth boundaries.

Yifan Wang, Andrew Liu, Richard Tucker et al.

We present a framework for automatically reconfiguring images of street scenes by populating, depopulating, or repopulating them with objects such as pedestrians or vehicles. Applications of this method include anonymizing images to enhance privacy, generating data augmentations for perception tasks like autonomous driving, and composing scenes to achieve a certain ambiance, such as empty streets in the early morning. At a technical level, our work has three primary contributions: (1) a method for clearing images of objects, (2) a method for estimating sun direction from a single image, and (3) a way to compose objects in scenes that respects scene geometry and illumination. Each component is learned from data with minimal ground truth annotations, by making creative use of large-numbers of short image bursts of street scenes. We demonstrate convincing results on a range of street scenes and illustrate potential applications.

Yifan Wang, Zhanxuan Mei, Chia-Yang Tsai et al.

The design of the optimal inverse discrete cosine transform (IDCT) to compensate the quantization error is proposed for effective lossy image compression in this work. The forward and inverse DCTs are designed in pair in current image/video coding standards without taking the quantization effect into account. Yet, the distribution of quantized DCT coefficients deviate from that of original DCT coefficients. This is particularly obvious when the quality factor of JPEG compressed images is small. To address this problem, we first use a set of training images to learn the compound effect of forward DCT, quantization and dequantization in cascade. Then, a new IDCT kernel is learned to reverse the effect of such a pipeline. Experiments are conducted to demonstrate that the advantage of the new method, which has a gain of 0.11-0.30dB over the standard JPEG over a wide range of quality factors.

Mozhdeh Rouhsedaghat, Yifan Wang, Shuowen Hu et al.

A non-parametric low-resolution face recognition model for resource-constrained environments with limited networking and computing is proposed in this work. Such environments often demand a small model capable of being effectively trained on a small number of labeled data samples, with low training complexity, and low-resolution input images. To address these challenges, we adopt an emerging explainable machine learning methodology called successive subspace learning (SSL).SSL offers an explainable non-parametric model that flexibly trades the model size for verification performance. Its training complexity is significantly lower since its model is trained in a one-pass feedforward manner without backpropagation. Furthermore, active learning can be conveniently incorporated to reduce the labeling cost. The effectiveness of the proposed model is demonstrated by experiments on the LFW and the CMU Multi-PIE datasets.

Mozhdeh Rouhsedaghat, Yifan Wang, Xiou Ge et al.

A light-weight low-resolution face gender classification method, called FaceHop, is proposed in this research. We have witnessed rapid progress in face gender classification accuracy due to the adoption of deep learning (DL) technology. Yet, DL-based systems are not suitable for resource-constrained environments with limited networking and computing. FaceHop offers an interpretable non-parametric machine learning solution. It has desired characteristics such as a small model size, a small training data amount, low training complexity, and low-resolution input images. FaceHop is developed with the successive subspace learning (SSL) principle and built upon the foundation of PixelHop++. The effectiveness of the FaceHop method is demonstrated by experiments. For gray-scale face images of resolution $32 \times 32$ in the LFW and the CMU Multi-PIE datasets, FaceHop achieves correct gender classification rates of 94.63% and 95.12% with model sizes of 16.9K and 17.6K parameters, respectively. It outperforms LeNet-5 in classification accuracy while LeNet-5 has a model size of 75.8K parameters.

Yifan Wang, Brian Curless, Steve Seitz

By analyzing the motion of people and other objects in a scene, we demonstrate how to infer depth, occlusion, lighting, and shadow information from video taken from a single camera viewpoint. This information is then used to composite new objects into the same scene with a high degree of automation and realism. In particular, when a user places a new object (2D cut-out) in the image, it is automatically rescaled, relit, occluded properly, and casts realistic shadows in the correct direction relative to the sun, and which conform properly to scene geometry. We demonstrate results (best viewed in supplementary video) on a range of scenes and compare to alternative methods for depth estimation and shadow compositing.

Wang Yifan, Shihao Wu, Hui Huang et al.

We present a detail-driven deep neural network for point set upsampling. A high-resolution point set is essential for point-based rendering and surface reconstruction. Inspired by the recent success of neural image super-resolution techniques, we progressively train a cascade of patch-based upsampling networks on different levels of detail end-to-end. We propose a series of architectural design contributions that lead to a substantial performance boost. The effect of each technical contribution is demonstrated in an ablation study. Qualitative and quantitative experiments show that our method significantly outperforms the state-of-the-art learning-based and optimazation-based approaches, both in terms of handling low-resolution inputs and revealing high-fidelity details.

Yifan Wang, Federico Perazzi, Brian McWilliams et al.

Recent deep learning approaches to single image super-resolution have achieved impressive results in terms of traditional error measures and perceptual quality. However, in each case it remains challenging to achieve high quality results for large upsampling factors. To this end, we propose a method (ProSR) that is progressive both in architecture and training: the network upsamples an image in intermediate steps, while the learning process is organized from easy to hard, as is done in curriculum learning. To obtain more photorealistic results, we design a generative adversarial network (GAN), named ProGanSR, that follows the same progressive multi-scale design principle. This not only allows to scale well to high upsampling factors (e.g., 8x) but constitutes a principled multi-scale approach that increases the reconstruction quality for all upsampling factors simultaneously. In particular ProSR ranks 2nd in terms of SSIM and 4th in terms of PSNR in the NTIRE2018 SISR challenge [34]. Compared to the top-ranking team, our model is marginally lower, but runs 5 times faster.

Yifan Wang, Lijun Wang, Hongyu Wang et al.

One impressive advantage of convolutional neural networks (CNNs) is their ability to automatically learn feature representation from raw pixels, eliminating the need for hand-designed procedures. However, recent methods for single image super-resolution (SR) fail to maintain this advantage. They utilize CNNs in two decoupled steps, i.e., first upsampling the low resolution (LR) image to the high resolution (HR) size with hand-designed techniques (e.g., bicubic interpolation), and then applying CNNs on the upsampled LR image to reconstruct HR results. In this paper, we seek an alternative and propose a new image SR method, which jointly learns the feature extraction, upsampling and HR reconstruction modules, yielding a completely end-to-end trainable deep CNN. As opposed to existing approaches, the proposed method conducts upsampling in the latent feature space with filters that are optimized for the task of image SR. In addition, the HR reconstruction is performed in a multi-scale manner to simultaneously incorporate both short- and long-range contextual information, ensuring more accurate restoration of HR images. To facilitate network training, a new training approach is designed, which jointly trains the proposed deep network with a relatively shallow network, leading to faster convergence and more superior performance. The proposed method is extensively evaluated on widely adopted data sets and improves the performance of state-of-the-art methods with a considerable margin. Moreover, in-depth ablation studies are conducted to verify the contribution of different network designs to image SR, providing additional insights for future research.