REVIEW 8 cited by
HumanEdit: A High-Quality Human-Rewarded Dataset for Instruction-based Image Editing
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
abstract
We present HumanEdit, a high-quality, human-rewarded dataset specifically designed for instruction-guided image editing, enabling precise and diverse image manipulations through open-form language instructions. Previous large-scale editing datasets often incorporate minimal human feedback, leading to challenges in aligning datasets with human preferences. HumanEdit bridges this gap by employing human annotators to construct data pairs and administrators to provide feedback. With meticulously curation, HumanEdit comprises 5,751 images and requires more than 2,500 hours of human effort across four stages, ensuring both accuracy and reliability for a wide range of image editing tasks. The dataset includes six distinct types of editing instructions: Action, Add, Counting, Relation, Remove, and Replace, encompassing a broad spectrum of real-world scenarios. All images in the dataset are accompanied by masks, and for a subset of the data, we ensure that the instructions are sufficiently detailed to support mask-free editing. Furthermore, HumanEdit offers comprehensive diversity and high-resolution $1024 \times 1024$ content sourced from various domains, setting a new versatile benchmark for instructional image editing datasets. With the aim of advancing future research and establishing evaluation benchmarks in the field of image editing, we release HumanEdit at https://huggingface.co/datasets/BryanW/HumanEdit.
Forward citations
Cited by 8 Pith papers
-
AInimation: Animating from Prompt to AI-Generated Responses
Animating prompt elements into their positions in an AI response improved users' ability to locate content, spot edits, and verify instructions in three lab experiments with 16 participants.
-
DanceOPD: On-Policy Generative Field Distillation
Hard-routed, single low-noise on-policy velocity matching composes conflicting image-generation capabilities into one flow student better than joint training, merging, or dense OPD baselines.
-
Trade-offs in Image Generation: How Do Different Dimensions Interact?
A new benchmark and VLM-as-judge metric map trade-offs among ten image-generation dimensions across 14 models, with a visualization called DTM.
-
ComplexBench-Edit: Benchmarking Complex Instruction-Driven Image Editing via Compositional Dependencies
Introduces a benchmark for chain-dependent image editing instructions plus a region-aware consistency metric, and shows a chain-of-thought prompt improves a Gemini-based editor.
-
KRIS-Bench: Benchmarking Next-Level Intelligent Image Editing Models
A new benchmark, KRIS-Bench, evaluates image editing models on knowledge-grounded reasoning across factual, conceptual, and procedural tasks, and finds large performance gaps in current models.
-
SRUM: Fine-Grained Self-Rewarding for Unified Multimodal Models
A unified multimodal model can improve its own text-to-image generation by using its understanding module as a rewarder in a global-plus-local reward-weighted training loop.
-
Track Any Anomalous Object: A Granular Video Anomaly Detection Pipeline
TAO pipelines object-centric anomaly scores into SAM2 prompts with a temporal consistency filter to obtain pixel-level anomaly segmentation and tracking.
-
MIND-Edit: MLLM Insight-Driven Editing via Language-Vision Projection
MIND-Edit combines instruction rewriting with MLLM-derived visual embeddings to guide diffusion-based image editing, but the reported numbers only partly support the claim of state-of-the-art performance.
Discussion (0). Sign in to comment.