HM3D offers 1000 building-scale 3D environments that are larger and higher-fidelity than existing datasets, enabling better-performing embodied AI agents for tasks like PointGoal navigation.
hub Mixed citations
Demystifying MMD GANs
Mixed citation behavior. Most common role is method (50%).
32
Pith papers citing it
Method
50% of classified citations
abstract
We investigate the training and performance of generative adversarial networks using the Maximum Mean Discrepancy (MMD) as critic, termed MMD GANs. As our main theoretical contribution, we clarify the situation with bias in GAN loss functions raised by recent work: we show that gradient estimators used in the optimization process for both MMD GANs and Wasserstein GANs are unbiased, but learning a discriminator based on samples leads to biased gradients for the generator parameters. We also discuss the issue of kernel choice for the MMD critic, and characterize the kernel corresponding to the energy distance used for the Cramer GAN critic. Being an integral probability metric, the MMD benefits from training strategies recently developed for Wasserstein GANs. In experiments, the MMD GAN is able to employ a smaller critic network than the Wasserstein GAN, resulting in a simpler and faster-training algorithm with matching performance. We also propose an improved measure of GAN convergence, the Kernel Inception Distance, and show how to use it to dynamically adapt learning rates during GAN training.
hub tools
citation-role summary
method 3
background 2
dataset 1
citation-polarity summary
representative citing papers
MDIC uses a text-conditioned diffusion decoder and a supervised feature-mask generator on visual side information to achieve SOTA perceptual quality in distributed image compression at extremely low bitrates.
SeamCam quantifies camouflage by computing one minus the highest IoU recoverable from category-conditioned detection proposals against a ground-truth mask, achieving 78.82% agreement with human judgments.
DirectTryOn achieves state-of-the-art one-step virtual try-on performance by applying pure conditional transport, garment preservation loss, and self-consistency loss to straighten trajectories in pretrained generative models.
STRIDE boosts diversity in one-step diffusion models by injecting PCA-aligned pink noise into transformer features while preserving text alignment and quality.
FaithEIR combines learnable reversible latent transformations, an adaptive high-frequency detail prior, and semantic conditioning to outperform prior methods in fidelity and perceptual quality for extreme image rescaling.
OccDirector uses a VLM-guided Spatio-Temporal MMDiT model with history anchoring to generate physically plausible 4D occupancy from language scripts, supported by the new OccInteract-85k dataset.
FIT is a large-scale dataset of 1.13M try-on triplets with exact size data plus a synthetic generation pipeline that enables training of virtual try-on models capable of depicting realistic garment fit including ill-fit cases.
Dress-ED is the first large-scale benchmark unifying virtual try-on, try-off, and text-guided garment editing with 146k verified samples plus a multimodal diffusion baseline.
Differentiable nonconformity scores induce flows that sample conformal prediction set boundaries, and mixing flows across levels produces conformal predictive distributions whose quantiles match the sets.
MAGIC is a few-shot mask-guided anomaly inpainting framework using Gaussian prompt perturbation, spatially adaptive guidance, and context-aware mask alignment to produce high-fidelity, diverse anomalies that outperform prior methods on downstream detection tasks.
Diffusion models solve noisy (non)linear inverse problems via approximated posterior sampling that blends diffusion steps with manifold gradients without strict consistency projection.
SDEdit performs guided image synthesis and editing by adding noise to inputs and refining them via denoising with a diffusion model's SDE prior, outperforming GAN methods in human studies without task-specific training.
A constrained optimization framework for diffusion model unlearning via KL and likelihood constraints, with duality results and reported better retention-unlearning tradeoffs than weight-based baselines.
TOPOS creates high-fidelity 3D heads with fixed industry topology from single images via a specialized VAE with Perceiver Resampler and a rectified flow transformer.
CRAFT adapts diffusion models to medical images via clinical reward alignment from LLMs and VLMs, improving alignment scores and cutting low-quality generations by 20.4% on average across modalities.
Anisotropic SPDEs preserve geometric data structure over longer timescales in score-based generative modeling, yielding better image quality than standard SDE baselines and flow matching in unconditional and conditional tasks.
A technique for parametric stylistic control in latent diffusion models learns disentangled directions from synthetic datasets and applies them via guidance composition while preserving semantics.
Optimizing initial noise via backpropagation approximation and spectral parameterization in structured 3D latent diffusion yields higher contextual consistency and prompt alignment in training-free inpainting.
FashionStylist is an expert-annotated benchmark dataset that unifies outfit-to-item grounding, completion, and evaluation tasks for multimodal large language models in fashion.
O2MAG generates high-fidelity text-guided anomalies from a single image without training by manipulating self-attention in diffusion models with anomaly masks and dual enhancements.
RefTon is a flux-based virtual try-on method that uses unpaired reference images of the target garment on different people to guide texture and detail preservation in a streamlined person-to-person pipeline without body parsing or masks.
InternScenes is a new dataset of approximately 40,000 simulatable indoor scenes that combines real scans, procedural, and designer sources, preserves small objects for realistic layouts, and includes processing for simulation and interaction.
UniCodec uses LLM-driven semantic disentanglement at the encoder and diffusion-based compositional generation at the decoder to enable one codec for both human perception and machine vision tasks without task-specific retraining.
citing papers explorer
-
Habitat-Matterport 3D Dataset (HM3D): 1000 Large-scale 3D Environments for Embodied AI
HM3D offers 1000 building-scale 3D environments that are larger and higher-fidelity than existing datasets, enabling better-performing embodied AI agents for tasks like PointGoal navigation.
-
Distributed Image Compression with Multimodal Side Information at Extremely Low Bitrates
MDIC uses a text-conditioned diffusion decoder and a supervised feature-mask generator on visual side information to achieve SOTA perceptual quality in distributed image compression at extremely low bitrates.
-
SeamCam: Quantifying Seamless Camouflage via Multi-Cue Visual Detectability
SeamCam quantifies camouflage by computing one minus the highest IoU recoverable from category-conditioned detection proposals against a ground-truth mask, achieving 78.82% agreement with human judgments.
-
DirectTryOn: One-Step Virtual Try-On via Straightened Conditional Transport
DirectTryOn achieves state-of-the-art one-step virtual try-on performance by applying pure conditional transport, garment preservation loss, and self-consistency loss to straighten trajectories in pretrained generative models.
-
STRIDE: Training-Free Diversity Guidance via PCA-Directed Feature Perturbation in Single-Step Diffusion Models
STRIDE boosts diversity in one-step diffusion models by injecting PCA-aligned pink noise into transformer features while preserving text alignment and quality.
-
Faithful Extreme Image Rescaling with Learnable Reversible Transformation and Semantic Priors
FaithEIR combines learnable reversible latent transformations, an adaptive high-frequency detail prior, and semantic conditioning to outperform prior methods in fidelity and perceptual quality for extreme image rescaling.
-
OccDirector: Language-Guided Behavior and Interaction Generation in 4D Occupancy Space
OccDirector uses a VLM-guided Spatio-Temporal MMDiT model with history anchoring to generate physically plausible 4D occupancy from language scripts, supported by the new OccInteract-85k dataset.
-
FIT: A Large-Scale Dataset for Fit-Aware Virtual Try-On
FIT is a large-scale dataset of 1.13M try-on triplets with exact size data plus a synthetic generation pipeline that enables training of virtual try-on models capable of depicting realistic garment fit including ill-fit cases.
-
Dress-ED: Instruction-Guided Editing for Virtual Try-On and Try-Off
Dress-ED is the first large-scale benchmark unifying virtual try-on, try-off, and text-guided garment editing with 146k verified samples plus a multimodal diffusion baseline.
-
Flow-Based Conformal Predictive Distributions
Differentiable nonconformity scores induce flows that sample conformal prediction set boundaries, and mixing flows across levels produces conformal predictive distributions whose quantiles match the sets.
-
MAGIC: Few-Shot Mask-Guided Anomaly Inpainting with Prompt Perturbation, Spatially Adaptive Guidance, and Context Awareness
MAGIC is a few-shot mask-guided anomaly inpainting framework using Gaussian prompt perturbation, spatially adaptive guidance, and context-aware mask alignment to produce high-fidelity, diverse anomalies that outperform prior methods on downstream detection tasks.
-
Diffusion Posterior Sampling for General Noisy Inverse Problems
Diffusion models solve noisy (non)linear inverse problems via approximated posterior sampling that blends diffusion steps with manifold gradients without strict consistency projection.
-
SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations
SDEdit performs guided image synthesis and editing by adding noise to inputs and refining them via denoising with a diffusion model's SDE prior, outperforming GAN methods in human studies without task-specific training.
-
Unlearning in Diffusion Models: A Unified Framework with KL Divergence and Likelihood Constraints
A constrained optimization framework for diffusion model unlearning via KL and likelihood constraints, with duality results and reported better retention-unlearning tradeoffs than weight-based baselines.
-
TOPOS: High-Fidelity and Efficient Industry-Grade 3D Head Generation
TOPOS creates high-fidelity 3D heads with fixed industry topology from single images via a specialized VAE with Perceiver Resampler and a rectified flow transformer.
-
CRAFT: Clinical Reward-Aligned Finetuning for Medical Image Synthesis
CRAFT adapts diffusion models to medical images via clinical reward alignment from LLMs and VLMs, improving alignment scores and cutting low-quality generations by 20.4% on average across modalities.
-
Score-Based Generative Modeling through Anisotropic Stochastic Partial Differential Equations
Anisotropic SPDEs preserve geometric data structure over longer timescales in score-based generative modeling, yielding better image quality than standard SDE baselines and flow matching in unconditional and conditional tasks.
-
Stylistic Attribute Control in Latent Diffusion Models
A technique for parametric stylistic control in latent diffusion models learns disentangled directions from synthetic datasets and applies them via guidance composition while preserving semantics.
-
InpaintSLat: Inpainting Structured 3D Latents via Initial Noise Optimization
Optimizing initial noise via backpropagation approximation and spectral parameterization in structured 3D latent diffusion yields higher contextual consistency and prompt alignment in training-free inpainting.
-
FashionStylist: An Expert Knowledge-enhanced Multimodal Dataset for Fashion Understanding
FashionStylist is an expert-annotated benchmark dataset that unifies outfit-to-item grounding, completion, and evaluation tasks for multimodal large language models in fashion.
-
One-to-More: High-Fidelity Training-Free Anomaly Generation with Attention Control
O2MAG generates high-fidelity text-guided anomalies from a single image without training by manipulating self-attention in diffusion models with anomaly masks and dual enhancements.
-
RefTon: Reference person shot assist virtual Try-on
RefTon is a flux-based virtual try-on method that uses unpaired reference images of the target garment on different people to guide texture and detail preservation in a streamlined person-to-person pipeline without body parsing or masks.
-
InternScenes: A Large-scale Simulatable Indoor Scene Dataset with Realistic Layouts
InternScenes is a new dataset of approximately 40,000 simulatable indoor scenes that combines real scans, procedural, and designer sources, preserves small objects for realistic layouts, and includes processing for simulation and interaction.
-
Semantics Disentanglement and Composition for Universal Image Coding with Efficiently LLM Reasoning and Generative Diffusion
UniCodec uses LLM-driven semantic disentanglement at the encoder and diffusion-based compositional generation at the decoder to enable one codec for both human perception and machine vision tasks without task-specific retraining.
-
Conjuring Semantic Similarity
Semantic similarity between texts is measured by the Jeffreys divergence between the image distributions induced by conditioning a diffusion model on each text, computed via Monte-Carlo sampling of the reverse-time SDEs.
-
CaloArt: Large-Patch x-Prediction Diffusion Transformers for High-Granularity Calorimeter Shower Generation
CaloArt achieves top FPD, high-level, and classifier metrics on CaloChallenge datasets 2 and 3 while keeping single-GPU generation at 9-11 ms per shower by combining large-patch tokenization, x-prediction, and conditional flow matching.
-
SAMIC: A Lightweight Semantic-Aware Mamba for Efficient Perceptual Image Compression
SAMIC introduces semantic-aware Mamba blocks and SVD-based redundancy reduction to achieve efficient perceptual image compression with improved rate-distortion-perception tradeoffs.
-
LoRaQ: Optimized Low Rank Approximation for 4-bit Quantization
LoRaQ enables fully sub-16-bit quantized diffusion models by optimizing low-rank error compensation in a data-free way, outperforming prior methods at equal memory cost on Pixart-Σ and SANA while supporting mixed low-precision branches.
-
Protecting and Preserving Protest Dynamics for Responsible Analysis
A responsible computing framework substitutes real protest imagery with labeled synthetic reproductions from conditional image synthesis to enable privacy-aware analysis of collective action patterns.
-
RectifiedHR: Enable Efficient High-Resolution Synthesis via Energy Rectification
RectifiedHR is a training-free method that uses noise refresh and latent energy analysis to enable efficient high-resolution synthesis in diffusion models.
- Active Sampling for Ultra-Low-Bit-Rate Video Compression via Conditional Controlled Diffusion
- Learning to Emulate Chaos: Adversarial Optimal Transport Regularization