Computer Vision

SpikeSlicer: An adaptive event stream slicer using a spiking neural network (SNN) to efficiently split events for improved downstream processing in object tracking and recognition.

SFCNet, a novel spherical frustum sparse convolution network, tackles LiDAR point cloud semantic segmentation by eliminating quantized information loss, leading to superior performance, especially for…

SpelsNet, a novel neural architecture, achieves accurate 3D point cloud segmentation into surface primitives by incorporating B-Rep graph structure supervision, leading to topologically consistent res…

SpeechForensics leverages audio-visual speech representation learning to achieve superior face forgery detection, outperforming state-of-the-art methods in cross-dataset generalization and robustness.

Spec-Gaussian enhances 3D Gaussian splatting by using anisotropic spherical Gaussians for view-dependent appearance modeling, achieving superior real-time rendering of scenes with specular and anisotr…

STIR: A novel spatio-temporal network reconstructs high-quality images from spiking camera data by jointly refining motion and intensity information for efficient and accurate high-speed imaging.

SparseAGS: High-fidelity 3D reconstruction & camera pose estimation from sparse views via generative synthesis.

Scattered Online Inference (SOI) drastically cuts down ANN computational complexity by leveraging data continuity and prediction seasonality, enabling faster real-time inference on low-power devices.

Soft Tensor Product Representations (Soft TPRs) revolutionize compositional visual representation learning by seamlessly blending continuous vector spaces and compositional structures, leading to supe…

Soft Superpixel Neighborhood Attention (SNA) optimally denoises images by incorporating superpixel probabilities into an attention module, outperforming traditional methods.

Smoothed Energy Guidance (SEG) improves unconditional image generation by reducing self-attention’s energy curvature, leading to higher-quality outputs with fewer artifacts.

SlotSSMs: a novel framework for modular sequence modeling, achieving significant performance gains by incorporating independent mechanisms and sparse interactions into State Space Models.

SlimSAM achieves near original SAM performance using 0.1% of its training data by employing a novel alternate slimming framework and disturbed Taylor pruning, significantly advancing data-efficient mo…

Scala: One-shot training enables flexible ViT inference!

Dual-Stream Interactive Transformers (DSIT) revolutionizes single image reflection separation by using a novel dual-attention mechanism that captures inter- and intra-layer correlations, significantly…

Simple and Fast Distillation (SFD) drastically accelerates diffusion model training by 1000x, achieving state-of-the-art results in few-step image generation with minimal fine-tuning.

ShowMaker: Generating high-fidelity 2D human conversational videos using fine-grained diffusion modeling and 2D key points.

SHMT: Self-supervised Hierarchical Makeup Transfer uses latent diffusion models to realistically and precisely apply diverse makeup styles to faces, even without paired training data, achieving high f…

SemanIR boosts image restoration efficiency by cleverly sharing key semantic information within Transformer layers, achieving state-of-the-art results across multiple tasks.

SfPUEL: A novel end-to-end SfP method achieves robust single-shot surface normal estimation under diverse lighting, integrating PS priors and material segmentation.