DF3DV-1K supplies 1,048 scenes with clean and cluttered image pairs plus a challenging 41-scene subset to benchmark and improve distractor-free radiance field methods.
hub
Realx3d: A physically-degraded 3d benchmark for multi-view visual restoration and recon- struction
13 Pith papers cite this work. Polarity classification is still indexing.
13
Pith papers citing it
hub tools
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 13years
2026 13roles
background 1polarities
unclear 1representative citing papers
FluxFlow uses conservative pixel-space flow-matching with uncertainty weights and Wiener test-time correction to outperform baselines on photometric and scientific accuracy for ground-to-space super-resolution, validated on a new real 19,500-pair DESI-HST dataset.
Dehaze-then-Splat uses per-frame generative dehazing followed by physics-regularized 3D Gaussian Splatting to achieve 20.98 dB PSNR and 0.683 SSIM on the Akikaze scene, a 1.5 dB gain over baseline by mitigating cross-view inconsistencies.
NAKA-GS combines bionics-inspired Naka chroma correction with progressive point pruning to boost restoration quality and efficiency in low-light 3D Gaussian Splatting.
A framework that combines MLLM-based image enhancement with a medium-aware 3D Gaussian Splatting model to reconstruct and render smoke scenes.
CLIP-guided selection of external data plus staged NAFNet training and inference fusion provides an effective pipeline for nighttime image dehazing in the NTIRE 2026 challenge.
ELoG-GS integrates geometry-aware initialization and luminance-guided photometric adaptation into Gaussian Splatting, achieving PSNR 18.66 and SSIM 0.69 on the NTIRE 2026 Track 1 low-light 3D reconstruction benchmark.
A dual-branch training-free ensemble fuses a hybrid attention network with a Mamba-based model via weighted combination to enhance super-resolution PSNR on DIV2K x4.
Dual-branch fusion of HAT-L and MambaIRv2-L with eight-way ensemble and equal-weight averaging outperforms single branches on PSNR, SSIM, and challenge score for infrared super-resolution.
SmokeGS-R uses refined dark channel prior for pseudo-clean supervision to train 3DGS geometry, followed by ensemble-based appearance harmonization, achieving PSNR 15.21 and outperforming baselines on smoke restoration challenge data.
A multi-stage pipeline of restoration, dehazing, MLLM enhancement and 3D Gaussian Splatting with MCMC averaging achieves first place in the NTIRE 2026 smoke-degraded novel view synthesis track.
Expanding training data diversity, adopting two-stage optimization, and applying geometric self-ensemble raises Restormer performance on Gaussian color denoising at sigma=50 by 3.366 dB PSNR on the NTIRE 2026 validation set.
The NTIRE 2026 challenge reports measurable progress in 3D reconstruction pipelines that handle real-world low-light and smoke degradation via the RealX3D benchmark.
citing papers explorer
-
DF3DV-1K: A Large-Scale Dataset and Benchmark for Distractor-Free Novel View Synthesis
DF3DV-1K supplies 1,048 scenes with clean and cluttered image pairs plus a challenging 41-scene subset to benchmark and improve distractor-free radiance field methods.
-
FluxFlow: Conservative Flow-Matching for Astronomical Image Super-Resolution
FluxFlow uses conservative pixel-space flow-matching with uncertainty weights and Wiener test-time correction to outperform baselines on photometric and scientific accuracy for ground-to-space super-resolution, validated on a new real 19,500-pair DESI-HST dataset.
-
Dehaze-then-Splat: Generative Dehazing with Physics-Informed 3D Gaussian Splatting for Smoke-Free Novel View Synthesis
Dehaze-then-Splat uses per-frame generative dehazing followed by physics-regularized 3D Gaussian Splatting to achieve 20.98 dB PSNR and 0.683 SSIM on the Akikaze scene, a 1.5 dB gain over baseline by mitigating cross-view inconsistencies.
-
Naka-GS: A Bionics-inspired Dual-Branch Naka Correction and Progressive Point Pruning for Low-Light 3DGS
NAKA-GS combines bionics-inspired Naka chroma correction with progressive point pruning to boost restoration quality and efficiency in low-light 3D Gaussian Splatting.
-
3D Smoke Scene Reconstruction Guided by Vision Priors from Multimodal Large Language Models
A framework that combines MLLM-based image enhancement with a medium-aware 3D Gaussian Splatting model to reconstruct and render smoke scenes.
-
CLIP-Guided Data Augmentation for Night-Time Image Dehazing
CLIP-guided selection of external data plus staged NAFNet training and inference fusion provides an effective pipeline for nighttime image dehazing in the NTIRE 2026 challenge.
-
ELoG-GS: Dual-Branch Gaussian Splatting with Luminance-Guided Enhancement for Extreme Low-light 3D Reconstruction
ELoG-GS integrates geometry-aware initialization and luminance-guided photometric adaptation into Gaussian Splatting, achieving PSNR 18.66 and SSIM 0.69 on the NTIRE 2026 Track 1 low-light 3D reconstruction benchmark.
-
Training-Free Model Ensemble for Single-Image Super-Resolution via Strong-Branch Compensation
A dual-branch training-free ensemble fuses a hybrid attention network with a Mamba-based model via weighted combination to enhance super-resolution PSNR on DIV2K x4.
-
Dual-Branch Remote Sensing Infrared Image Super-Resolution
Dual-branch fusion of HAT-L and MambaIRv2-L with eight-way ensemble and equal-weight averaging outperforms single branches on PSNR, SSIM, and challenge score for infrared super-resolution.
-
SmokeGS-R: Physics-Guided Pseudo-Clean 3DGS for Real-World Multi-View Smoke Restoration
SmokeGS-R uses refined dark channel prior for pseudo-clean supervision to train 3DGS geometry, followed by ensemble-based appearance harmonization, achieving PSNR 15.21 and outperforming baselines on smoke restoration challenge data.
-
GenSmoke-GS: A Multi-Stage Method for Novel View Synthesis from Smoke-Degraded Images Using a Generative Model
A multi-stage pipeline of restoration, dehazing, MLLM enhancement and 3D Gaussian Splatting with MCMC averaging achieves first place in the NTIRE 2026 smoke-degraded novel view synthesis track.
-
Beyond Model Design: Data-Centric Training and Self-Ensemble for Gaussian Color Image Denoising
Expanding training data diversity, adopting two-stage optimization, and applying geometric self-ensemble raises Restormer performance on Gaussian color denoising at sigma=50 by 3.366 dB PSNR on the NTIRE 2026 validation set.
-
NTIRE 2026 3D Restoration and Reconstruction in Real-world Adverse Conditions: RealX3D Challenge Results
The NTIRE 2026 challenge reports measurable progress in 3D reconstruction pipelines that handle real-world low-light and smoke degradation via the RealX3D benchmark.