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%).
49
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
A diffusion-trained maximum entropy model uses 512 learned statistics to synthesize visual textures at quality matching or exceeding prior models that rely on ~177k statistics.
A unifying framework decomposes concept alignment into instance-wise and distributional translation and concept consistency, introduces the InterVenchA benchmark, and shows that joint optimization via CoSAE recovers strong alignment even with 0.1% paired data.
TrioPose proposes a Triple-Stream Pose-Aware DiT with relational bias masks and spatial loss weighting to achieve SOTA pose-guided text-to-image results on multi-person benchmarks like Human-Art.
A bag-of-position-tagged-words embedding guides text-to-image diffusion models as effectively as full contextual text embeddings from standard encoders.
FAV aligns few-step generative models by amortizing SVGD updates from reward-tilted sampling into generator parameters via fixed-point regression, requiring only sample access, and shows outperformance on robotics tasks plus scaling on image generators.
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.
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 saliency-guided warp-unwarp method reallocates spatial representation to preserve fine structures in latent diffusion models for image-to-image translation.
SatSplatDiff combines depth supervision and shadow-guided generative refinement with 2DGS to reduce geometric MAE by up to 18% and improve visual fidelity by 28-45% on satellite datasets while enabling 5x resolution enhancement.
HiFiVe is a training-free framework using an auto-regressive texture refinement pipeline with depth-based warping, multi-view fusion, and symmetry to enhance both texture and geometry fidelity in vehicle generation from 2D priors.
C3VD-DEFCOL supplies 110 videos from 11 colon meshes with paired realistic RGB appearance and dense time-resolved 3D ground truth under three levels of parameterized peristaltic deformation for benchmarking deformable reconstruction.
SPRDiff is a diffusion model for ultra-low bitrate image compression that fuses features from distortion-oriented, semantic-oriented, and VAE encoders plus a dual-feature reconstruction module to outperform prior methods on rate-distortion-perception trade-offs.
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.
citing papers explorer
-
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.
-
Text-Driven 3D Indoor Scene Synthesis in Non-Manhattan Environments
SPG-Layout combines statistical object priors with hierarchical large-object-first placement to produce physically plausible text-driven 3D scenes in non-Manhattan rooms and outperforms baselines on a new 500-scene benchmark.