Results 21 to 30 of about 168,620 (333)
PlenOctrees for Real-time Rendering of Neural Radiance Fields [PDF]
IEEE International Conference on Computer Vision, 2021 We introduce a method to render Neural Radiance Fields (NeRFs) in real time using PlenOctrees, an octree-based 3D representation which supports view-dependent effects.
Alex Yu +5 more
semanticscholar +1 more source
Point-NeRF: Point-based Neural Radiance Fields [PDF]
Computer Vision and Pattern Recognition, 2022 Volumetric neural rendering methods like NeRF [34] generate high-quality view synthesis results but are optimized per-scene leading to prohibitive reconstruction time.
Qiangeng Xu +6 more
semanticscholar +1 more source
Robust Dynamic Radiance Fields [PDF]
Computer Vision and Pattern Recognition, 2023 Dynamic radiance field reconstruction methods aim to model the time-varying structure and appearance of a dynamic scene. Existing methods, however, assume that accurate camera poses can be reliably estimated by Structure from Motion (SfM) algorithms ...
Y. Liu +8 more
semanticscholar +1 more source
NoPe-NeRF: Optimising Neural Radiance Field with No Pose Prior [PDF]
Computer Vision and Pattern Recognition, 2022 Training a Neural Radiance Field (NeRF) without precomputed camera poses is challenging. Recent advances in this direction demonstrate the possibility of jointly optimising a NeRF and camera poses in forward-facing scenes.
Wenjing Bian +4 more
semanticscholar +1 more source
MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereo [PDF]
IEEE International Conference on Computer Vision, 2021 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, we propose a ...
Anpei Chen +6 more
semanticscholar +1 more source
D-NeRF: Neural Radiance Fields for Dynamic Scenes [PDF]
Computer Vision and Pattern Recognition, 2020 Neural rendering techniques combining machine learning with geometric reasoning have arisen as one of the most promising approaches for synthesizing novel views of a scene from a sparse set of images.
Albert Pumarola +3 more
semanticscholar +1 more source
NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collections [PDF]
Computer Vision and Pattern Recognition, 2020 We present a learning-based method for synthesizing novel views of complex scenes using only unstructured collections of in-the-wild photographs. We build on Neural Radiance Fields (NeRF), which uses the weights of a multi-layer perceptron to model the ...
Ricardo Martin-Brualla +5 more
semanticscholar +1 more source
UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstruction [PDF]
IEEE International Conference on Computer Vision, 2021 Neural implicit 3D representations have emerged as a powerful paradigm for reconstructing surfaces from multi-view images and synthesizing novel views.
Michael Oechsle +2 more
semanticscholar +1 more source
BARF: Bundle-Adjusting Neural Radiance Fields [PDF]
IEEE International Conference on Computer Vision, 2021 Neural Radiance Fields (NeRF) [31] have recently gained a surge of interest within the computer vision community for its power to synthesize photorealistic novel views of real-world scenes.
Chen-Hsuan Lin +3 more
semanticscholar +1 more source
Nerfies: Deformable Neural Radiance Fields [PDF]
IEEE International Conference on Computer Vision, 2020 We present the first method capable of photorealistically reconstructing deformable scenes using photos/videos captured casually from mobile phones. Our approach augments neural radiance fields (NeRF) by optimizing an additional continuous volumetric ...
Keunhong Park +6 more
semanticscholar +1 more source