lpips
PulseAugur coverage of lpips — every cluster mentioning lpips across labs, papers, and developer communities, ranked by signal.
3 day(s) with sentiment data
-
AI data quality metrics misaligned with human perception and task performance
A new paper published on arXiv explores the disconnect between automated data quality metrics and their actual utility for deep learning models, particularly in Earth observation. The research highlights that common met…
-
TeleMorpher framework enables robust simultaneous motion-location video editing
Researchers have introduced TeleMorpher, a novel framework designed for simultaneous motion and location editing in videos. This one-shot approach disentangles subjects from backgrounds, applies pose warping using motio…
-
AI-generated image detector fragility exposed in new audit · 2 sources tracked
A new audit of training-free AI-generated image detectors reveals significant fragility and inconsistencies. The study found that implementation details, such as the choice of backbone network (e.g., AlexNet vs. VGG-16)…
-
Video quality models fall short in assessing AI super-resolution, study finds
A new paper investigates the effectiveness of current video quality assessment models for evaluating diffusion-based video super-resolution (VSR) methods. The study found that while CNN-based full-reference models like …
-
PixelGen paper introduces perceptual supervision to boost pixel diffusion image generation
Researchers have introduced PixelGen, a novel end-to-end pixel diffusion framework designed to enhance image generation quality. PixelGen incorporates perceptual losses, specifically LPIPS for local textures and P-DINO …
-
ViTok-v2 scales to 5B parameters, advancing image autoencoder reconstruction and generation
Researchers have introduced ViTok-v2, a 5-billion parameter image autoencoder that scales to larger resolutions and parameter counts than previous models. This new model utilizes native resolution support and a DINOv3 p…
-
Researchers develop new differentiable VQ for optimized generative image compression
Researchers have developed RDVQ, a novel framework for optimizing generative image compression. This approach uses a differentiable relaxation of the codebook distribution to enable end-to-end rate-distortion optimizati…
-
GOR-IS framework improves 3D object removal with intrinsic space inpainting
Researchers have developed GOR-IS, a new framework for removing objects from 3D scene reconstructions generated by methods like 3D Gaussian Splatting. This approach addresses limitations in existing techniques by explic…
-
Researchers develop pHVI-ISPNet for improved night photography rendering
Researchers have developed a new framework called pHVI-ISPNet to improve night photography rendering by addressing perceptual distortions and color bias. This RAW-to-RGB model utilizes specific refinements like RAW-doma…
-
Parameter-Efficient Architectural Modifications for Translation-Invariant CNNs
Researchers have developed a novel 'Online Architecture' strategy for Convolutional Neural Networks (CNNs) that significantly enhances translation invariance. By strategically inserting Global Average Pooling (GAP) laye…