Papers with Code 아카이브

Novel View Synthesis

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

하위 태스크: 2
평가표: 24
보존된 평가 기록: 103

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>

코드

관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.

https://github.com/cvg/depthsplat

공식 코드

DepthSplat: Connecting Gaussian Splatting and Depth

https://github.com/cvlab-columbia/zero123

공식 코드

Zero-1-to-3: Zero-shot One Image to 3D Object

https://github.com/cvlab-kaist/PF3plat

공식 코드

PF3plat: Pose-Free Feed-Forward 3D Gaussian Splatting

https://github.com/cwchenwang/NeRF-SR

공식 코드

NeRF-SR: High-Quality Neural Radiance Fields using Supersampling

https://github.com/cyhsu14/OmniNeRF

공식 코드

Moving in a 360 World: Synthesizing Panoramic Parallaxes from a Single Panorama

https://github.com/dadonda89/DDNeRF

공식 코드

DDNeRF: Depth Distribution Neural Radiance Fields

https://github.com/darglein/ADOP

공식 코드

ADOP: Approximate Differentiable One-Pixel Point Rendering

https://github.com/david-svitov/BBSplat

공식 코드

BillBoard Splatting (BBSplat): Learnable Textured Primitives for Novel View Synthesis

https://github.com/dazinovic/neural-rgbd-surface-reconstruction

공식 코드

Neural RGB-D Surface Reconstruction

https://github.com/dcharatan/flowmap

공식 코드

FlowMap: High-Quality Camera Poses, Intrinsics, and Depth via Gradient Descent

https://github.com/dcharatan/pixelsplat

공식 코드

pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstruction

https://github.com/deepmind/functa

공식 코드

From data to functa: Your data point is a function and you can treat it like one

https://github.com/deguchihiroyuki/e2gs

공식 코드

E2GS: Event Enhanced Gaussian Splatting

https://github.com/dehezhang2/point_based_nerf_editing

공식 코드

Point-Based Radiance Fields for Controllable Human Motion Synthesis

https://github.com/divyakraman/aerialbooth2023

공식 코드

HawkI: Homography & Mutual Information Guidance for 3D-free Single Image to Aerial View

https://github.com/divyakraman/hawki2024

공식 코드

HawkI: Homography & Mutual Information Guidance for 3D-free Single Image to Aerial View

https://github.com/dogyoonlee/dp-nerf

공식 코드

DP-NeRF: Deblurred Neural Radiance Field with Physical Scene Priors

https://github.com/donydchen/matchnerf

공식 코드

Explicit Correspondence Matching for Generalizable Neural Radiance Fields

https://github.com/donydchen/mvsplat

공식 코드

MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Images

https://github.com/donydchen/mvsplat360

공식 코드

MVSplat360: Feed-Forward 360 Scene Synthesis from Sparse Views

https://github.com/dreamguo/UNIKD

공식 코드

UNIKD: UNcertainty-filtered Incremental Knowledge Distillation for Neural Implicit Representation

https://github.com/dreamscene4d/dreamscene4d

공식 코드

DreamScene4D: Dynamic Multi-Object Scene Generation from Monocular Videos

https://github.com/dtc111111/neslam

공식 코드

NeSLAM: Neural Implicit Mapping and Self-Supervised Feature Tracking With Depth Completion and Denoising

https://github.com/dtc111111/sn-lidar

공식 코드

SN-LiDAR: Semantic Neural Fields for Novel Space-time View LiDAR Synthesis

https://github.com/dwawayu/pensieve

공식 코드

Recollection from Pensieve: Novel View Synthesis via Learning from Uncalibrated Videos

https://github.com/eckertzhang/text2nerf

공식 코드

Text2NeRF: Text-Driven 3D Scene Generation with Neural Radiance Fields

https://github.com/edm-research/cut-and-splat

공식 코드

Cut-and-Splat: Leveraging Gaussian Splatting for Synthetic Data Generation

https://github.com/eezkni/colnerf

공식 코드

ColNeRF: Collaboration for Generalizable Sparse Input Neural Radiance Field

https://github.com/eldar/flash3d

공식 코드

Flash3D: Feed-Forward Generalisable 3D Scene Reconstruction from a Single Image

https://github.com/envision-research/driverecon

공식 코드

DrivingRecon: Large 4D Gaussian Reconstruction Model For Autonomous Driving

https://github.com/esa/snerf

공식 코드

Shadow Neural Radiance Fields for Multi-view Satellite Photogrammetry

https://github.com/ethanweber/nerfbusters

공식 코드

Nerfbusters: Removing Ghostly Artifacts from Casually Captured NeRFs

https://github.com/ethz-asl/neusurfemb

공식 코드

NeuSurfEmb: A Complete Pipeline for Dense Correspondence-based 6D Object Pose Estimation without CAD Models

https://github.com/ewrfcas/arci

공식 코드

LeftRefill: Filling Right Canvas based on Left Reference through Generalized Text-to-Image Diffusion Model

https://github.com/ewrfcas/leftrefill

공식 코드

LeftRefill: Filling Right Canvas based on Left Reference through Generalized Text-to-Image Diffusion Model

https://github.com/ewrfcas/mvgenmaster

공식 코드

MVGenMaster: Scaling Multi-View Generation from Any Image via 3D Priors Enhanced Diffusion Model

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.