Search Results for author:
Found 32 papers, 16 papers with code
Rethinking Reflection in Pre-Training
A language model's ability to reflect on its own reasoning provides a key advantage for solving complex problems.
SwiftTry: Fast and Consistent Video Virtual Try-On with Diffusion Models
Given an input video of a person and a new garment, the objective of this paper is to synthesize a new video where the person is wearing the specified garment while maintaining spatiotemporal consistency.
SwiftEdit: Lightning Fast Text-Guided Image Editing via One-Step Diffusion
Recent advances in text-guided image editing enable users to perform image edits through simple text inputs, leveraging the extensive priors of multi-step diffusion-based text-to-image models.
EditScout: Locating Forged Regions from Diffusion-based Edited Images with Multimodal LLM
By leveraging the contextual and semantic strengths of LLMs, our framework achieves promising results on MagicBrush, AutoSplice, and PerfBrush (novel diffusion-based dataset) datasets, outperforming previous approaches in mIoU and F1-score metrics.
SNOOPI: Supercharged One-step Diffusion Distillation with Proper Guidance
However, our study reveals its instability when handling different diffusion model backbones due to using a fixed guidance scale within the Variational Score Distillation (VSD) loss.
ModeDreamer: Mode Guiding Score Distillation for Text-to-3D Generation using Reference Image Prompts
Existing Score Distillation Sampling (SDS)-based methods have driven significant progress in text-to-3D generation.
SharpDepth: Sharpening Metric Depth Predictions Using Diffusion Distillation
We propose SharpDepth, a novel approach to monocular metric depth estimation that combines the metric accuracy of discriminative depth estimation methods (e. g., Metric3D, UniDepth) with the fine-grained boundary sharpness typically achieved by generative methods (e. g., Marigold, Lotus).
Any3DIS: Class-Agnostic 3D Instance Segmentation by 2D Mask Tracking
Existing 3D instance segmentation methods frequently encounter issues with over-segmentation, leading to redundant and inaccurate 3D proposals that complicate downstream tasks.
SwiftBrush v2: Make Your One-step Diffusion Model Better Than Its Teacher
Remarkably, by combining the weights of models trained with efficient LoRA and full training, we achieve a new state-of-the-art one-step diffusion model, achieving an FID of 8. 14 and surpassing all GAN-based and multi-step Stable Diffusion models.
Open-Ended 3D Point Cloud Instance Segmentation
To mitigate this constraint, we propose a novel problem termed Open-Ended 3D Instance Segmentation (OE-3DIS), which eliminates the necessity for predefined class names during testing.
Semi-supervised 3D Semantic Scene Completion with 2D Vision Foundation Model Guidance
Accurate prediction of 3D semantic occupancy from 2D visual images is vital in enabling autonomous agents to comprehend their surroundings for planning and navigation.
3D Semantic Occupancy Prediction
3D Semantic Scene Completion
OpenSUN3D: 1st Workshop Challenge on Open-Vocabulary 3D Scene Understanding
This report provides an overview of the challenge hosted at the OpenSUN3D Workshop on Open-Vocabulary 3D Scene Understanding held in conjunction with ICCV 2023.
Open3DIS: Open-Vocabulary 3D Instance Segmentation with 2D Mask Guidance
We introduce Open3DIS, a novel solution designed to tackle the problem of Open-Vocabulary Instance Segmentation within 3D scenes.
Ranked #1 on
3D Open-Vocabulary Instance Segmentation
on S3DIS
3D Instance Segmentation
3D Open-Vocabulary Instance Segmentation
+4
Stable Messenger: Steganography for Message-Concealed Image Generation
In the ever-expanding digital landscape, safeguarding sensitive information remains paramount.
DiverseDream: Diverse Text-to-3D Synthesis with Augmented Text Embedding
Text-to-3D synthesis has recently emerged as a new approach to sampling 3D models by adopting pretrained text-to-image models as guiding visual priors.
LP-OVOD: Open-Vocabulary Object Detection by Linear Probing
To address this issue, we propose a novel method, LP-OVOD, that discards low-quality boxes by training a sigmoid linear classifier on pseudo labels retrieved from the top relevant region proposals to the novel text.
Ranked #6 on
Open Vocabulary Object Detection
on MSCOCO
Dataset Diffusion: Diffusion-based Synthetic Dataset Generation for Pixel-Level Semantic Segmentation
To address this, generative models have emerged as an effective solution for generating synthetic data.
GaPro: Box-Supervised 3D Point Cloud Instance Segmentation Using Gaussian Processes as Pseudo Labelers
Furthermore, we demonstrate the robustness of our approach, where we can adapt various state-of-the-art fully supervised methods to the weak supervision task by using our pseudo labels for training.
ISBNet: a 3D Point Cloud Instance Segmentation Network with Instance-aware Sampling and Box-aware Dynamic Convolution
Existing 3D instance segmentation methods are predominated by the bottom-up design -- manually fine-tuned algorithm to group points into clusters followed by a refinement network.
Ranked #4 on
3D Instance Segmentation
on ScanNet200
PSENet: Progressive Self-Enhancement Network for Unsupervised Extreme-Light Image Enhancement
The extremes of lighting (e. g. too much or too little light) usually cause many troubles for machine and human vision.
Few-shot Object Counting and Detection
We tackle a new task of few-shot object counting and detection.
Ranked #4 on
Few-shot Object Counting and Detection
on FSC147
Few-shot Object Counting and Detection
Few-Shot Object Detection
+1
Geodesic-Former: a Geodesic-Guided Few-shot 3D Point Cloud Instance Segmenter
This paper introduces a new problem in 3D point cloud: few-shot instance segmentation.
Inductive and Transductive Few-Shot Video Classification via Appearance and Temporal Alignments
To the best of our knowledge, our work is the first to explore transductive few-shot video classification.
POODLE: Improving Few-shot Learning via Penalizing Out-of-Distribution Samples
In this work, we propose to use out-of-distribution samples, i. e., unlabeled samples coming from outside the target classes, to improve few-shot learning.
iFS-RCNN: An Incremental Few-shot Instance Segmenter
This paper addresses incremental few-shot instance segmentation, where a few examples of new object classes arrive when access to training examples of old classes is not available anymore, and the goal is to perform well on both old and new classes.
POODLE: Improving Few-shot Learning via Penalizing Out-of-Distribution Samples NeurIPS 2021
In this work, we propose to use out-of-distribution samples, i. e., unlabeled samples coming from outside the target classes, to improve few-shot learning.
A Weakly Supervised Amodal Segmenter with Boundary Uncertainty Estimation
The resulting predictions on training images are taken as the pseudo-ground truth for the standard training of Mask-RCNN, which we use for amodal instance segmentation of test images.
Semi-Supervising Learning, Transfer Learning, and Knowledge Distillation with SimCLR
Most successful semi-supervised learning approaches in computer vision focus on leveraging huge amount of unlabeled data, learning the general representation via data augmentation and transformation, creating pseudo labels, implementing different loss functions, and eventually transferring this knowledge to more task-specific smaller models.
FAPIS: A Few-shot Anchor-free Part-based Instance Segmenter
This paper is about few-shot instance segmentation, where training and test image sets do not share the same object classes.
A Self-supervised GAN for Unsupervised Few-shot Object Recognition
This paper addresses unsupervised few-shot object recognition, where all training images are unlabeled, and test images are divided into queries and a few labeled support images per object class of interest.
Feature Weighting and Boosting for Few-Shot Segmentation
Finally, the target object is segmented in the query image by using a cosine similarity between the class feature vector and the query's feature map.
Ranked #80 on
Few-Shot Semantic Segmentation
on COCO-20i (5-shot)
Causal Mediation Analysis Leveraging Multiple Types of Summary Statistics Data
We can achieve necessary interpretation of GWAS in a causal mediation framework, looking to establish a sparse set of mediators between genetic and downstream variables, but there are several challenges.
