Removal Coherence (RC) metrics, which compare local feature distributions in masked versus background regions via sliding-window MMD, align with human judgments of object-removal quality substantially better than existing metrics.
hub
Diffueraser: A diffusion model for video inpainting
15 Pith papers cite this work. Polarity classification is still indexing.
15
Pith papers citing it
hub tools
representative citing papers
Sparkle supplies a large-scale dataset and benchmark for instruction-driven video background replacement, enabling models that generate more natural and temporally consistent new scenes than earlier approaches.
YOSE accelerates DiT video object removal up to 2.5x by using BVI for adaptive token selection and DiffSim to simulate unmasked token effects, while preserving visual quality.
The PVIR benchmark tests video object removal on physical consistency using 95 annotated videos and shows that existing methods struggle with complex interactions like lingering shadows.
VideoCoF adds an explicit reasoning step using edit-region latents in video diffusion models to enable precise mask-free editing and motion alignment with only 50k training pairs.
AlbedoEdit fine-tunes video foundation models to translate RGB videos into edited versions conditioned on user-edited first-frame albedo maps, trained on a new synthetic paired dataset for insertion, removal, and texture tasks.
Tube-structured incremental semantic HARQ reduces time-weighted recovery cost and enables earlier stabilization in generative video reconstruction compared to block-based methods under matched budgets and channel conditions.
NUMINA improves counting accuracy in text-to-video diffusion models by up to 7.4% via a training-free identify-then-guide framework on the new CountBench dataset.
GA-GS uses motion segmentation, diffusion-based inpainting for pseudo-ground-truth, and per-Gaussian authenticity scalars to achieve SOTA static scene reconstruction from videos with dynamic occlusions.
CLEAR achieves end-to-end mask-free video subtitle removal via dual-encoder self-supervised orthogonality and LoRA-based generation feedback, delivering +6.77 dB PSNR gains and strong zero-shot multilingual performance.
SVOR achieves stable, shadow-free video object removal under real-world imperfections via MUSE mask handling, DA-Seg localization, and curriculum training on real and synthetic data.
EditVerse unifies image and video editing and generation in one transformer model via unified token sequences and in-context learning, trained jointly on curated video editing data plus image/video corpora and evaluated on a new instruction-based benchmark.
Bernini is a framework that uses an MLLM planner to output semantic representations for a DiT renderer to generate or edit videos, reporting SOTA benchmark performance.
WorldAct activates monolithic 3D worlds into interactive scenes via multimodal agent-guided decomposition, geometrically aligned mesh reconstruction, and 3D inpainting.
citing papers explorer
-
PROVE: A Perceptual RemOVal cohErence Benchmark for Visual Media
Removal Coherence (RC) metrics, which compare local feature distributions in masked versus background regions via sliding-window MMD, align with human judgments of object-removal quality substantially better than existing metrics.
-
Sparkle: Realizing Lively Instruction-Guided Video Background Replacement via Decoupled Guidance
Sparkle supplies a large-scale dataset and benchmark for instruction-driven video background replacement, enabling models that generate more natural and temporally consistent new scenes than earlier approaches.
-
YOSE: You Only Select Essential Tokens for Efficient DiT-based Video Object Removal
YOSE accelerates DiT video object removal up to 2.5x by using BVI for adaptive token selection and DiffSim to simulate unmasked token effects, while preserving visual quality.
-
Physics-Aware Video Instance Removal Benchmark
The PVIR benchmark tests video object removal on physical consistency using 95 annotated videos and shows that existing methods struggle with complex interactions like lingering shadows.
-
VideoCoF: Unified Video Editing with Temporal Reasoner
VideoCoF adds an explicit reasoning step using edit-region latents in video diffusion models to enable precise mask-free editing and motion alignment with only 50k training pairs.
-
AlbedoEdit: Unified Instance-Level Video Editing with Albedo Guidance
AlbedoEdit fine-tunes video foundation models to translate RGB videos into edited versions conditioned on user-edited first-frame albedo maps, trained on a new synthetic paired dataset for insertion, removal, and texture tasks.
-
Tube-Structured Incremental Semantic HARQ for Generative Video Receivers
Tube-structured incremental semantic HARQ reduces time-weighted recovery cost and enables earlier stabilization in generative video reconstruction compared to block-based methods under matched budgets and channel conditions.
-
When Numbers Speak: Aligning Textual Numerals and Visual Instances in Text-to-Video Diffusion Models
NUMINA improves counting accuracy in text-to-video diffusion models by up to 7.4% via a training-free identify-then-guide framework on the new CountBench dataset.
-
GA-GS: Generation-Assisted Gaussian Splatting for Static Scene Reconstruction
GA-GS uses motion segmentation, diffusion-based inpainting for pseudo-ground-truth, and per-Gaussian authenticity scalars to achieve SOTA static scene reconstruction from videos with dynamic occlusions.
-
CLEAR: Context-Aware Learning with End-to-End Mask-Free Inference for Adaptive Video Subtitle Removal
CLEAR achieves end-to-end mask-free video subtitle removal via dual-encoder self-supervised orthogonality and LoRA-based generation feedback, delivering +6.77 dB PSNR gains and strong zero-shot multilingual performance.
-
From Ideal to Real: Stable Video Object Removal under Imperfect Conditions
SVOR achieves stable, shadow-free video object removal under real-world imperfections via MUSE mask handling, DA-Seg localization, and curriculum training on real and synthetic data.
-
EditVerse: Unifying Image and Video Editing and Generation with In-Context Learning
EditVerse unifies image and video editing and generation in one transformer model via unified token sequences and in-context learning, trained jointly on curated video editing data plus image/video corpora and evaluated on a new instruction-based benchmark.
-
Bernini: Latent Semantic Planning for Video Diffusion
Bernini is a framework that uses an MLLM planner to output semantic representations for a DiT renderer to generate or edit videos, reporting SOTA benchmark performance.
-
WorldAct: Activating Monolithic 3D Worlds into Interactive-Ready Object-Centric Scenes
WorldAct activates monolithic 3D worlds into interactive scenes via multimodal agent-guided decomposition, geometrically aligned mesh reconstruction, and 3D inpainting.
- DualEraser: Joint Video Object and Effect Removal via Balanced Text-Mask Guidance and Decoupled Locator-Preserver