Text-to-3D models lose prompt sensitivity for out-of-distribution shapes due to sink traps but retain geometric diversity via unconditional priors, enabling a decoupled inversion method for robust editing.
Diffusiondb: A large-scale prompt gallery dataset for text-to- image generative models
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
citation-role summary
dataset 2
background 1
citation-polarity summary
representative citing papers
SEED is a new benchmark for sequential provenance tracing in diffusion-edited deepfake faces, with the FAITH baseline showing that wavelet-based high-frequency signals aid detection of accumulated editing artifacts.
FakeReasoning is an MLLM-based framework for unified forgery detection and reasoning on AI-generated images, supported by the new MMFR-Dataset of 120K images and 378K annotations across 10 generators.
VASR separates continuation and residual variance in reward-guided diffusion SMC, using optimal mass allocation and systematic resampling to achieve up to 26% better FID scores and faster runtimes than prior SMC and MCTS methods.
Slot-MLLM introduces a slot-attention-based object-centric visual tokenizer with Q-Former encoder, diffusion decoder, and residual vector quantization for improved local visual comprehension and generation in multimodal LLMs.
HPD v2 is the largest human preference dataset for text-to-image images with 798k choices, and HPS v2 is the resulting CLIP-based scorer that better predicts human judgments and responds to model improvements.
ACPO uses anchor-based regularization with NR-IQA guidance to enable stable perceptual quality improvements in diffusion model fine-tuning.
This position paper contends that the concept of 'real' images must be rethought because most modern photographs are computationally generated, undermining current deepfake detection methods.
citing papers explorer
-
VASR: Variance-Aware Systematic Resampling for Reward-Guided Diffusion
VASR separates continuation and residual variance in reward-guided diffusion SMC, using optimal mass allocation and systematic resampling to achieve up to 26% better FID scores and faster runtimes than prior SMC and MCTS methods.