相关论文: Neural Lumigraph Rendering

Recent implicit neural representations have shown great results for novel view synthesis. However, existing methods require expensive per-scene optimization from many views hence limiting their application to real-world unbounded urban…

Neural radiance fields (NeRFs) have become a ubiquitous tool for modeling scene appearance and geometry from multiview imagery. Recent work has also begun to explore how to use additional supervision from lidar or depth sensor measurements…

Novel view synthesis (NVS) seeks to render photorealistic, 3D-consistent images of a scene from unseen camera poses given only a sparse set of posed views. Existing deterministic networks render observed regions quickly but blur unobserved…

Reconstructing real-world 3D objects has numerous applications in computer vision, such as virtual reality, video games, and animations. Ideally, 3D reconstruction methods should generate high-fidelity results with 3D consistency in…

We present a method for recovering the shape and radiance of a scene consisting of multiple people given solely a few images. Multi-human scenes are complex due to additional occlusion and clutter. For single-human settings, existing…

Various SDF-based neural implicit surface reconstruction methods have been proposed recently, and have demonstrated remarkable modeling capabilities. However, due to the global nature and limited representation ability of a single network,…

The recent research explosion around implicit neural representations, such as NeRF, shows that there is immense potential for implicitly storing high-quality scene and lighting information in compact neural networks. However, one major…

We propose a new view synthesis method via synthesizing a 3D neural field from both single or few-view input images. To address the ill-posed nature of the image-to-3D generation problem, we devise a two-stage method that involves a…

Implicit neural representation (INR) has proven to be accurate and efficient in various domains. In this work, we explore how different neural networks can be designed as a new texture INR, which operates in a continuous manner rather than…

Existing real-time RGB-D reconstruction approaches, like Kinect Fusion, lack real-time photo-realistic visualization. This is due to noisy, oversmoothed or incomplete geometry and blurry textures which are fused from imperfect depth maps…

Rendering scenes with a high-quality human face from arbitrary viewpoints is a practical and useful technique for many real-world applications. Recently, Neural Radiance Fields (NeRF), a rendering technique that uses neural networks to…

We propose a neural inverse rendering approach that jointly reconstructs geometry, spatially varying reflectance, and lighting conditions from multi-view images captured under varying directional lighting. Unlike prior multi-view…

In recent years, novel view synthesis has gained popularity in generating high-fidelity images. While demonstrating superior performance in the task of synthesizing novel views, the majority of these methods are still based on the…

Applying NeRF to downstream perception tasks for scene understanding and representation is becoming increasingly popular. Most existing methods treat semantic prediction as an additional rendering task, \textit{i.e.}, the "label rendering"…

3D head avatars built with neural implicit volumetric representations have achieved unprecedented levels of photorealism. However, the computational cost of these methods remains a significant barrier to their widespread adoption,…

We propose a neural inverse rendering pipeline called IRON that operates on photometric images and outputs high-quality 3D content in the format of triangle meshes and material textures readily deployable in existing graphics pipelines. Our…

We propose NEMTO, the first end-to-end neural rendering pipeline to model 3D transparent objects with complex geometry and unknown indices of refraction. Commonly used appearance modeling such as the Disney BSDF model cannot accurately…

Mathematically representing the shape of an object is a key ingredient for solving inverse rendering problems. Explicit representations like meshes are efficient to render in a differentiable fashion but have difficulties handling topology…

Recent advances in full-head reconstruction have been obtained by optimizing a neural field through differentiable surface or volume rendering to represent a single scene. While these techniques achieve an unprecedented accuracy, they take…

Classical light field rendering for novel view synthesis can accurately reproduce view-dependent effects such as reflection, refraction, and translucency, but requires a dense view sampling of the scene. Methods based on geometric…