SOTAVerified

Novel View Synthesis

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.

( Image credit: Multi-view to Novel view: Synthesizing novel views with Self-Learned Confidence )

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 51–100 of 1441 papers

TitleStatusHype
Lighting Every Darkness with 3DGS: Fast Training and Real-Time Rendering for HDR View SynthesisCode3
Flash3D: Feed-Forward Generalisable 3D Scene Reconstruction from a Single ImageCode3
GenWarp: Single Image to Novel Views with Semantic-Preserving Generative WarpingCode3
HDR-GS: Efficient High Dynamic Range Novel View Synthesis at 1000x Speed via Gaussian SplattingCode3
NVS-Solver: Video Diffusion Model as Zero-Shot Novel View SynthesizerCode3
DOGS: Distributed-Oriented Gaussian Splatting for Large-Scale 3D Reconstruction Via Gaussian ConsensusCode3
DreamScene4D: Dynamic Multi-Object Scene Generation from Monocular VideosCode3
LiDAR4D: Dynamic Neural Fields for Novel Space-time View LiDAR SynthesisCode3
GS2Mesh: Surface Reconstruction from Gaussian Splatting via Novel Stereo ViewsCode3
HAC: Hash-grid Assisted Context for 3D Gaussian Splatting CompressionCode3
Gaussian Splatting on the Move: Blur and Rolling Shutter Compensation for Natural Camera MotionCode3
BAD-Gaussians: Bundle Adjusted Deblur Gaussian SplattingCode3
SV3D: Novel Multi-view Synthesis and 3D Generation from a Single Image using Latent Video DiffusionCode3
Relaxing Accurate Initialization Constraint for 3D Gaussian SplattingCode3
DNGaussian: Optimizing Sparse-View 3D Gaussian Radiance Fields with Global-Local Depth NormalizationCode3
GES: Generalized Exponential Splatting for Efficient Radiance Field RenderingCode3
EscherNet: A Generative Model for Scalable View SynthesisCode3
StopThePop: Sorted Gaussian Splatting for View-Consistent Real-time RenderingCode3
Compact 3D Scene Representation via Self-Organizing Gaussian GridsCode3
pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D ReconstructionCode3
Mip-Splatting: Alias-free 3D Gaussian SplattingCode3
Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene ReconstructionCode3
Objaverse-XL: A Universe of 10M+ 3D ObjectsCode3
NeROIC: Neural Rendering of Objects from Online Image CollectionsCode3
3D Photography using Context-aware Layered Depth InpaintingCode3
NeRF: Representing Scenes as Neural Radiance Fields for View SynthesisCode3
SynSin: End-to-end View Synthesis from a Single ImageCode3
CGVQM+D: Computer Graphics Video Quality Metric and DatasetCode2
Speedy Deformable 3D Gaussian Splatting: Fast Rendering and Compression of Dynamic ScenesCode2
ZPressor: Bottleneck-Aware Compression for Scalable Feed-Forward 3DGSCode2
Recollection from Pensieve: Novel View Synthesis via Learning from Uncalibrated VideosCode2
Hybrid 3D-4D Gaussian Splatting for Fast Dynamic Scene RepresentationCode2
VRSplat: Fast and Robust Gaussian Splatting for Virtual RealityCode2
BlockGaussian: Efficient Large-Scale Scene Novel View Synthesis via Adaptive Block-Based Gaussian SplattingCode2
Luminance-GS: Adapting 3D Gaussian Splatting to Challenging Lighting Conditions with View-Adaptive Curve AdjustmentCode2
HoGS: Unified Near and Far Object Reconstruction via Homogeneous Gaussian SplattingCode2
Hardware-Rasterized Ray-Based Gaussian SplattingCode2
MTGS: Multi-Traversal Gaussian SplattingCode2
Niagara: Normal-Integrated Geometric Affine Field for Scene Reconstruction from a Single ViewCode2
3D Student Splatting and ScoopingCode2
Advancing Dense Endoscopic Reconstruction with Gaussian Splatting-driven Surface Normal-aware Tracking and MappingCode2
GS-LiDAR: Generating Realistic LiDAR Point Clouds with Panoramic Gaussian SplattingCode2
FatesGS: Fast and Accurate Sparse-View Surface Reconstruction using Gaussian Splatting with Depth-Feature ConsistencyCode2
MaskGaussian: Adaptive 3D Gaussian Representation from Probabilistic MasksCode2
DrivingRecon: Large 4D Gaussian Reconstruction Model For Autonomous DrivingCode2
From an Image to a Scene: Learning to Imagine the World from a Million 360 VideosCode2
Deblur4DGS: 4D Gaussian Splatting from Blurry Monocular VideoCode2
Momentum-GS: Momentum Gaussian Self-Distillation for High-Quality Large Scene ReconstructionCode2
HybridGS: Decoupling Transients and Statics with 2D and 3D Gaussian SplattingCode2
SfM-Free 3D Gaussian Splatting via Hierarchical TrainingCode2
Show:102550
← PrevPage 2 of 29Next →
All datasetsLLFFMip-NeRF 360NeRFTanks and TemplesRefRefDONeRF: Evaluation DatasetX3DRTMVScanNetACIDSWORDHDR-GS

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1TensoRF + NeRFLiXPSNR27.39—Unverified
2JAXNeRFPSNR26.92—Unverified
3K-Planes (hybrid)PSNR26.92—Unverified
4Plenoxels + NeRFLiXPSNR26.9—Unverified
5K-Planes (explicit)PSNR26.78—Unverified
6TensoRFPSNR26.73—Unverified
7NeRFPSNR26.5—Unverified
8PlenoxelsPSNR26.29—Unverified
9HyperReelPSNR26.2—Unverified
10MobileNeRFPSNR25.91—Unverified
#ModelMetricClaimedVerifiedStatus
1NeRFLPIPS0.52—Unverified
2MobileNeRFLPIPS0.47—Unverified
3NeRF++LPIPS0.43—Unverified
4C3DGSLPIPS0.25—Unverified
5Compressed 3D Gaussian SplattingLPIPS0.24—Unverified
6HAC 3DGSLPIPS0.23—Unverified
7Compact3DLPIPS0.23—Unverified
8Self-Organizing GaussiansLPIPS0.22—Unverified
93D Gaussian SplattingLPIPS0.21—Unverified
10LightGaussianLPIPS0.21—Unverified
#ModelMetricClaimedVerifiedStatus
1Deformable Beta SplattingPSNR34.66—Unverified
2Self-Organizing GaussiansPSNR33.7—Unverified
3I-NGPPSNR33.18—Unverified
4TensoRFPSNR33.14—Unverified
5K-Planes (hybrid)PSNR32.36—Unverified
6K-Planes (explicit)PSNR32.21—Unverified
7PlenoxelsPSNR31.71—Unverified
8JAXNeRFPSNR31.65—Unverified
9NeRFPSNR31—Unverified
10MobileNeRFPSNR30.9—Unverified
#ModelMetricClaimedVerifiedStatus
1TensoRF + NeRFLiX++PSNR29.24—Unverified
2TensoRF + NeRFLiXPSNR28.94—Unverified
3Plenoxels + NeRFLiXPSNR28.61—Unverified
4Self-Organizing GaussiansPSNR25.63—Unverified
5HAC 3DGSPSNR24.4—Unverified
6Compact3DPSNR23.47—Unverified
73D Gaussian SplattingPSNR23.14—Unverified
8Mip-NERF 360PSNR19.65—Unverified
9DIVeR + NeRFLiXSSIM0.92—Unverified
10C3DGSPSNR0.23—Unverified
#ModelMetricClaimedVerifiedStatus
1R3F-OracleAverage PSNR (dB)29.34—Unverified
2Zip-NeRFAverage PSNR (dB)26.11—Unverified
3R3FAverage PSNR (dB)24.95—Unverified
4Ray Deformation NetworkAverage PSNR (dB)23.13—Unverified
5Rose-NeRFAverage PSNR (dB)22.86—Unverified
6NeuSAverage PSNR (dB)19.62—Unverified
7SplatfactoAverage PSNR (dB)19.53—Unverified
8TNSRAverage PSNR (dB)18.64—Unverified
#ModelMetricClaimedVerifiedStatus
1HyperReelPSNR35.1—Unverified
2Instant NGPPSNR33.1—Unverified
3AdaNeRFPSNR30.9—Unverified
4NeRFPSNR30.9—Unverified
5DoNeRFPSNR30.8—Unverified
6TermiNeRFPSNR29.8—Unverified
#ModelMetricClaimedVerifiedStatus
1SAX-NeRFPSNR51.37—Unverified
2NAFPSNR38.81—Unverified
3TensoRFPSNR37.67—Unverified
4NeATPSNR36.01—Unverified
5NeRFPSNR32.49—Unverified
6InTomoPSNR31.96—Unverified
#ModelMetricClaimedVerifiedStatus
1Pixel-NeRF (env: Google Scan)PSNR14.59—Unverified
2Pixel-NeRF (env: Bricks)PSNR12.15—Unverified
3Pixel-NeRF (env: ABC)PSNR12.15—Unverified
4Pixel-NeRF (env: Amz. Ber.)PSNR12.13—Unverified
#ModelMetricClaimedVerifiedStatus
13DGEERPSNR31.5—Unverified
23DGUTPSNR30.64—Unverified
3EVERPSNR29.47—Unverified
4FisheyeGSPSNR27.81—Unverified
#ModelMetricClaimedVerifiedStatus
1impl.-nodepthFID42.88—Unverified
2hybridNLL5.34—Unverified
3impl.-catdepthSSIM0.42—Unverified
#ModelMetricClaimedVerifiedStatus
1StereoLayers (8 layers)LPIPS0.11—Unverified
2StereoLayers (2 layers)LPIPS0.1—Unverified
3StereoLayersLPIPS0.1—Unverified
#ModelMetricClaimedVerifiedStatus
1HDR-GSAverage PSNR38.37—Unverified
2HDR-NeRFAverage PSNR36.4—Unverified
#ModelMetricClaimedVerifiedStatus
1NeRFtrinsic FourAverage PSNR27.15—Unverified
2NeRF--Average PSNR23.92—Unverified
#ModelMetricClaimedVerifiedStatus
1HybridFID48.84—Unverified
2Impl.-depthNLL4.84—Unverified
#ModelMetricClaimedVerifiedStatus
1Gear-NeRFPSNR32.21—Unverified
#ModelMetricClaimedVerifiedStatus
1Self-Organizing GaussiansLPIPS0.26—Unverified
#ModelMetricClaimedVerifiedStatus
1Single NeRF + Share./Inst. NetLPIPS0.14—Unverified
#ModelMetricClaimedVerifiedStatus
1READAverage PSNR23.28—Unverified
#ModelMetricClaimedVerifiedStatus
1Multi-view to Novel ViewSSIM0.63—Unverified
#ModelMetricClaimedVerifiedStatus
1Single NeRF + Share./Inst. NetLPIPS0.02—Unverified
#ModelMetricClaimedVerifiedStatus
1Multi-view to Novel ViewSSIM0.92—Unverified
#ModelMetricClaimedVerifiedStatus
1Multi-view to Novel ViewSSIM0.9—Unverified
#ModelMetricClaimedVerifiedStatus
1Multi-view to Novel ViewSSIM0.7—Unverified