Search Results for author:
Found 18 papers, 11 papers with code
DepGraph: Towards Any Structural Pruning
Structural pruning enables model acceleration by removing structurally-grouped parameters from neural networks.
ONCE-3DLanes: Building Monocular 3D Lane Detection
We present ONCE-3DLanes, a real-world autonomous driving dataset with lane layout annotation in 3D space.
PoseTriplet: Co-evolving 3D Human Pose Estimation, Imitation, and Hallucination under Self-supervision
Existing self-supervised 3D human pose estimation schemes have largely relied on weak supervisions like consistency loss to guide the learning, which, inevitably, leads to inferior results in real-world scenarios with unseen poses.
Ranked #37 on
3D Human Pose Estimation
on MPI-INF-3DHP
Enhancing Video Super-Resolution via Implicit Resampling-based Alignment
We show that bilinear interpolation inherently attenuates high-frequency information while an MLP-based coordinate network can approximate more frequencies.
Ranked #1 on
Video Super-Resolution
on Vid4 - 4x upscaling
Point2Seq: Detecting 3D Objects as Sequences
We further propose a lightweight scene-to-sequence decoder that can auto-regressively generate words conditioned on features from a 3D scene as well as cues from the preceding words.
TM2D: Bimodality Driven 3D Dance Generation via Music-Text Integration
We propose a novel task for generating 3D dance movements that simultaneously incorporate both text and music modalities.
Improving Deep Regression with Ordinal Entropy
In computer vision, it is often observed that formulating regression problems as a classification task often yields better performance.
Ranked #16 on
Crowd Counting
on ShanghaiTech B
Lens-to-lens bokeh effect transformation. NTIRE 2023 challenge report
We present the new Bokeh Effect Transformation Dataset (BETD), and review the proposed solutions for this novel task at the NTIRE 2023 Bokeh Effect Transformation Challenge.
MotionMix: Weakly-Supervised Diffusion for Controllable Motion Generation
Specifically, we separate the denoising objectives of a diffusion model into two stages: obtaining conditional rough motion approximations in the initial $T-T^*$ steps by learning the noisy annotated motions, followed by the unconditional refinement of these preliminary motions during the last $T^*$ steps using unannotated motions.
Object Detection in Foggy Scenes by Embedding Depth and Reconstruction into Domain Adaptation
In our DA framework, we retain the depth and background information during the domain feature alignment.
PARTNER: Level up the Polar Representation for LiDAR 3D Object Detection
Recently, polar-based representation has shown promising properties in perceptual tasks.
Bias-Compensated Integral Regression for Human Pose Estimation
Experimental results on both the human body and hand benchmarks show that BCIR is faster to train and more accurate than the original integral regression, making it competitive with state-of-the-art detection methods.
Overcoming the Trade-off Between Accuracy and Plausibility in 3D Hand Shape Reconstruction
However, the reconstructed meshes are prone to artifacts and do not appear as plausible hand shapes.
Priority-Centric Human Motion Generation in Discrete Latent Space
We also present a motion discrete diffusion model that employs an innovative noise schedule, determined by the significance of each motion token within the entire motion sequence.
Learning Unorthogonalized Matrices for Rotation Estimation
Estimating 3D rotations is a common procedure for 3D computer vision.
DreamDrone
We introduce DreamDrone, an innovative method for generating unbounded flythrough scenes from textual prompts.
HEAP: Unsupervised Object Discovery and Localization with Contrastive Grouping
Further, to ensure the distinguishability among various regions, we introduce a region-level contrastive clustering loss to pull closer similar regions across images.
Semantic Segmentation in Multiple Adverse Weather Conditions with Domain Knowledge Retention
They struggle to acquire new knowledge while also retaining previously learned knowledge. To address these problems, we propose a semantic segmentation method for multiple adverse weather conditions that incorporates adaptive knowledge acquisition, pseudolabel blending, and weather composition replay.
