Anpei Chen
YOU?
Author Swipe
View article: TTT3R: 3D Reconstruction as Test-Time Training
TTT3R: 3D Reconstruction as Test-Time Training Open
Modern Recurrent Neural Networks have become a competitive architecture for 3D reconstruction due to their linear-time complexity. However, their performance degrades significantly when applied beyond the training context length, revealing…
View article: Ref-GS: Directional Factorization for 2D Gaussian Splatting
Ref-GS: Directional Factorization for 2D Gaussian Splatting Open
In this paper, we introduce Ref-GS, a novel approach for directional light factorization in 2D Gaussian splatting, which enables photorealistic view-dependent appearance rendering and precise geometry recovery. Ref-GS builds upon the defer…
View article: LaRa: Efficient Large-Baseline Radiance Fields
LaRa: Efficient Large-Baseline Radiance Fields Open
Radiance field methods have achieved photorealistic novel view synthesis and geometry reconstruction. But they are mostly applied in per-scene optimization or small-baseline settings. While several recent works investigate feed-forward rec…
View article: NeLF-Pro: Neural Light Field Probes for Multi-Scale Novel View Synthesis
NeLF-Pro: Neural Light Field Probes for Multi-Scale Novel View Synthesis Open
We present NeLF-Pro, a novel representation to model and reconstruct light fields in diverse natural scenes that vary in extent and spatial granularity. In contrast to previous fast reconstruction methods that represent the 3D scene global…
View article: GraphDreamer: Compositional 3D Scene Synthesis from Scene Graphs
GraphDreamer: Compositional 3D Scene Synthesis from Scene Graphs Open
As pretrained text-to-image diffusion models become increasingly powerful, recent efforts have been made to distill knowledge from these text-to-image pretrained models for optimizing a text-guided 3D model. Most of the existing methods ge…
View article: Mip-Splatting: Alias-free 3D Gaussian Splatting
Mip-Splatting: Alias-free 3D Gaussian Splatting Open
Recently, 3D Gaussian Splatting has demonstrated impressive novel view synthesis results, reaching high fidelity and efficiency. However, strong artifacts can be observed when changing the sampling rate, \eg, by changing focal length or ca…
View article: NeuManifold: Neural Watertight Manifold Reconstruction with Efficient and High-Quality Rendering Support
NeuManifold: Neural Watertight Manifold Reconstruction with Efficient and High-Quality Rendering Support Open
We present a method for generating high-quality watertight manifold meshes from multi-view input images. Existing volumetric rendering methods are robust in optimization but tend to generate noisy meshes with poor topology. Differentiable …
View article: Single-Stage Diffusion NeRF: A Unified Approach to 3D Generation and Reconstruction
Single-Stage Diffusion NeRF: A Unified Approach to 3D Generation and Reconstruction Open
3D-aware image synthesis encompasses a variety of tasks, such as scene generation and novel view synthesis from images. Despite numerous task-specific methods, developing a comprehensive model remains challenging. In this paper, we present…
View article: Factor Fields: A Unified Framework for Neural Fields and Beyond
Factor Fields: A Unified Framework for Neural Fields and Beyond Open
We present Factor Fields, a novel framework for modeling and representing signals. Factor Fields decomposes a signal into a product of factors, each represented by a classical or neural field representation which operates on transformed in…
View article: ICARUS
ICARUS Open
The practical deployment of Neural Radiance Fields (NeRF) in rendering applications faces several challenges, with the most critical one being low rendering speed on even high-end graphic processing units (GPUs). In this paper, we present …
View article: NeRFPlayer: A Streamable Dynamic Scene Representation with Decomposed Neural Radiance Fields
NeRFPlayer: A Streamable Dynamic Scene Representation with Decomposed Neural Radiance Fields Open
Visually exploring in a real-world 4D spatiotemporal space freely in VR has been a long-term quest. The task is especially appealing when only a few or even single RGB cameras are used for capturing the dynamic scene. To this end, we prese…
View article: Anisotropic Fourier Features for Neural Image-Based Rendering and Relighting
Anisotropic Fourier Features for Neural Image-Based Rendering and Relighting Open
Recent neural rendering techniques have greatly benefited image-based modeling and relighting tasks. They provide a continuous, compact, and parallelable representation by modeling the plenoptic function as multilayer perceptrons (MLPs). H…
View article: PREF: Phasorial Embedding Fields for Compact Neural Representations
PREF: Phasorial Embedding Fields for Compact Neural Representations Open
We present an efficient frequency-based neural representation termed PREF: a shallow MLP augmented with a phasor volume that covers significant border spectra than previous Fourier feature mapping or Positional Encoding. At the core is our…
View article: TensoRF: Tensorial Radiance Fields
TensoRF: Tensorial Radiance Fields Open
We present TensoRF, a novel approach to model and reconstruct radiance fields. Unlike NeRF that purely uses MLPs, we model the radiance field of a scene as a 4D tensor, which represents a 3D voxel grid with per-voxel multi-channel features…
View article: ICARUS: A Specialized Architecture for Neural Radiance Fields Rendering
ICARUS: A Specialized Architecture for Neural Radiance Fields Rendering Open
The practical deployment of Neural Radiance Fields (NeRF) in rendering applications faces several challenges, with the most critical one being low rendering speed on even high-end graphic processing units (GPUs). In this paper, we present …
View article: SofGAN: A Portrait Image Generator with Dynamic Styling
SofGAN: A Portrait Image Generator with Dynamic Styling Open
Recently, Generative Adversarial Networks (GANs) have been widely used for portrait image generation. However, in the latent space learned by GANs, different attributes, such as pose, shape, and texture style, are generally entangled, maki…
View article: GNeRF: GAN-based Neural Radiance Field without Posed Camera
GNeRF: GAN-based Neural Radiance Field without Posed Camera Open
We introduce GNeRF, a framework to marry Generative Adversarial Networks (GAN) with Neural Radiance Field (NeRF) reconstruction for the complex scenarios with unknown and even randomly initialized camera poses. Recent NeRF-based advances h…
View article: Convolutional Neural Opacity Radiance Fields
Convolutional Neural Opacity Radiance Fields Open
Photo-realistic modeling and rendering of fuzzy objects with complex opacity are critical for numerous immersive VR/AR applications, but it suffers from strong view-dependent brightness, color. In this paper, we propose a novel scheme to g…
View article: MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereo
MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereo Open
We present MVSNeRF, a novel neural rendering approach that can efficiently reconstruct neural radiance fields for view synthesis. Unlike prior works on neural radiance fields that consider per-scene optimization on densely captured images,…
View article: A Free Viewpoint Portrait Generator with Dynamic Styling.
A Free Viewpoint Portrait Generator with Dynamic Styling. Open
Generating portrait images from a single latent space facing the problem of entangled attributes, making it difficult to explicitly adjust the generation on specific attributes, e.g., contour and viewpoint control or dynamic styling. There…
View article: A Neural Rendering Framework for Free-Viewpoint Relighting
A Neural Rendering Framework for Free-Viewpoint Relighting Open
We present a novel Relightable Neural Renderer (RNR) for simultaneous view synthesis and relighting using multi-view image inputs. Existing neural rendering (NR) does not explicitly model the physical rendering process and hence has limite…
View article: Photo-Realistic Facial Details Synthesis From Single Image
Photo-Realistic Facial Details Synthesis From Single Image Open
We present a single-image 3D face synthesis technique that can handle challenging facial expressions while recovering fine geometric details. Our technique employs expression analysis for proxy face geometry generation and combines supervi…
View article: Photo-Realistic Facial Details Synthesis from Single Image
Photo-Realistic Facial Details Synthesis from Single Image Open
We present a single-image 3D face synthesis technique that can handle challenging facial expressions while recovering fine geometric details. Our technique employs expression analysis for proxy face geometry generation and combines supervi…
View article: Sparse Photometric 3D Face Reconstruction Guided by Morphable Models
Sparse Photometric 3D Face Reconstruction Guided by Morphable Models Open
We present a novel 3D face reconstruction technique that leverages sparse photometric stereo (PS) and latest advances on face registration/modeling from a single image. We observe that 3D morphable faces approach provides a reasonable geom…