https://github.com/hjr37/CG-SLAM
CG-SLAM: Efficient Dense RGB-D SLAM in a Consistent Uncertainty-aware 3D Gaussian Field
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
Synthesize a target image with an arbitrary target camera pose from given source images and their camera poses.
See Wiki for more introductions.
The Synthesis method include: NeRF, MPI and so on.
<span style="color:grey; opacity: 0.6">( Image credit: Multi-view to Novel view: Synthesizing novel views with Self-Learned Confidence )</span>
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
CG-SLAM: Efficient Dense RGB-D SLAM in a Consistent Uncertainty-aware 3D Gaussian Field
2D Gaussian Splatting for Geometrically Accurate Radiance Fields
HUGSIM: A Real-Time, Photo-Realistic and Closed-Loop Simulator for Autonomous Driving
Liquid Warping GAN with Attention: A Unified Framework for Human Image Synthesis
Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene Reconstruction
NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction
NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis
NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis
I$^2$-SDF: Intrinsic Indoor Scene Reconstruction and Editing via Raytracing in Neural SDFs
Instant Neural Graphics Primitives with a Multiresolution Hash Encoding
NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis
Feature 3DGS: Supercharging 3D Gaussian Splatting to Enable Distilled Feature Fields
Vision Transformer for NeRF-Based View Synthesis from a Single Input Image
NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis
NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis
NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis
NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis
NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis
Instant Neural Graphics Primitives with a Multiresolution Hash Encoding
GARF: Gaussian Activated Radiance Fields for High Fidelity Reconstruction and Pose Estimation
Deferred Neural Rendering: Image Synthesis using Neural Textures
CityGaussian: Real-time High-quality Large-Scale Scene Rendering with Gaussians
360MonoDepth: High-Resolution 360° Monocular Depth Estimation
NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis
Gear-NeRF: Free-Viewpoint Rendering and Tracking with Motion-aware Spatio-Temporal Sampling
InfoNeRF: Ray Entropy Minimization for Few-Shot Neural Volume Rendering
NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction
NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.