Incorporating physics into data-driven computer vision
Many computer vision techniques infer properties of our physical world from images.
Although images are formed through the physics of light and mechanics, computer vision …
Although images are formed through the physics of light and mechanics, computer vision …
Sv3d: Novel multi-view synthesis and 3d generation from a single image using latent video diffusion
Abstract We present Stable Video 3D (SV3D)—a latent video diffusion model for high-
resolution, image-to-multi-view generation of orbital videos around a 3D object. Recent …
resolution, image-to-multi-view generation of orbital videos around a 3D object. Recent …
Sugar: Surface-aligned gaussian splatting for efficient 3d mesh reconstruction and high-quality mesh rendering
We propose a method to allow precise and extremely fast mesh extraction from 3D Gaussian
Splatting. Gaussian Splatting has recently become very popular as it yields realistic …
Splatting. Gaussian Splatting has recently become very popular as it yields realistic …
Relightable 3d gaussians: Realistic point cloud relighting with brdf decomposition and ray tracing
In this paper, we present a novel differentiable point-based rendering framework to achieve
photo-realistic relighting. To make the reconstructed scene relightable, we enhance vanilla …
photo-realistic relighting. To make the reconstructed scene relightable, we enhance vanilla …
F2-nerf: Fast neural radiance field training with free camera trajectories
This paper presents a novel grid-based NeRF called F^ 2-NeRF (Fast-Free-NeRF) for novel
view synthesis, which enables arbitrary input camera trajectories and only costs a few …
view synthesis, which enables arbitrary input camera trajectories and only costs a few …
Bakedsdf: Meshing neural sdfs for real-time view synthesis
We present a method for reconstructing high-quality meshes of large unbounded real-world
scenes suitable for photorealistic novel view synthesis. We first optimize a hybrid neural …
scenes suitable for photorealistic novel view synthesis. We first optimize a hybrid neural …
Ref-nerf: Structured view-dependent appearance for neural radiance fields
Neural Radiance Fields (NeRF) is a popular view synthesis technique that represents a
scene as a continuous volumetric function, parameterized by multilayer perceptrons that …
scene as a continuous volumetric function, parameterized by multilayer perceptrons that …
Delicate textured mesh recovery from nerf via adaptive surface refinement
Abstract Neural Radiance Fields (NeRF) have constituted a remarkable breakthrough in
image-based 3D reconstruction. However, their implicit volumetric representations differ …
image-based 3D reconstruction. However, their implicit volumetric representations differ …
Extracting triangular 3d models, materials, and lighting from images
We present an efficient method for joint optimization of topology, materials and lighting from
multi-view image observations. Unlike recent multi-view reconstruction approaches, which …
multi-view image observations. Unlike recent multi-view reconstruction approaches, which …
Neus: Learning neural implicit surfaces by volume rendering for multi-view reconstruction
We present a novel neural surface reconstruction method, called NeuS, for reconstructing
objects and scenes with high fidelity from 2D image inputs. Existing neural surface …
objects and scenes with high fidelity from 2D image inputs. Existing neural surface …