Single Image Object Counting and Localizing using Active-Learning

Huberman-Spiegelglas, Inbar; Fattal, Raanan

doi:10.1109/wacv51458.2022.00377

Cited by 4 publications

(10 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Input Text Refinement PRedItOR [191], ReDiffuser [192], Captioning and Injection [193], InstructEdit [194] Inversion/Sampling Modification Direct Inversion [195], DDPM Inversion [196], SDE-Drag [197], LEDITS++ [198], FEC [199], EMILIE [200], Negative Inversion [201], Proximal Inversion [202], Null-Text Guidance [203], EDICT [204], AIDI [205], CycleDiffusion [206], InjectFusion [207], Fixed-point inversion [208], TIC [209], Diffusion Brush [210], Self-guidance [211] Attention Modification P2P [212], Pix2Pix-Zero [213], MasaCtrl [85], PnP [214], TF-ICON [215], Object-Shape Variations [216], Conditional Score Guidance [217], EBMs [218], Shape-Guided Diffusion [219], HD-Painter [220] Mask Guidance…”

Section: Training and Finetuning Free Approachesmentioning

confidence: 99%

“…Modification of inversion and sampling formulas are common techniques in training and finetuning free methods [195], [196], [201]. The inversion process is used to invert a real image into a noisy latent space, and then the sampling process is used to generate an edited result given the target prompt.…”

Section: Inversion/sampling Modificationmentioning

confidence: 99%

“…The inversion process is used to invert a real image into a noisy latent space, and then the sampling process is used to generate an edited result given the target prompt. Among them, DDIM Inversion [18] is the most commonly used baseline method, although it often leads to the failure of reconstructing the source image [196], [201], [204]. Direct Inversion [195] pioneers a paradigm that edits a real image by changing the source prompt to the target prompt, showcasing its ability to handle diverse tasks.…”

Section: Inversion/sampling Modificationmentioning

confidence: 99%

“…However, it still faces the reconstruction failure problem. Thus, several methods [196], [201], [204] modify the inversion and sampling formulas to improve the reconstruction capability. Reconstruction Information Memory.…”

Section: Inversion/sampling Modificationmentioning

confidence: 99%

“…(Continued on the next page) [180] Text ✓ DragonDiffusion [181] Dragging Points ✓ ✓ ✓ ✓ ✓ ✓ DragDiffusion [182] Dragging Points ✓ ✓ ✓ DDS [183] Text [190] Text ✓ ✓ ✓ ✓ PRedItOR [191] Text ✓ ✓ ✓ ✓ ✓ ✓ ReDiffuser [192] Text ✓ ✓ ✓ ✓ Captioning and Injection [193] Text ✓ ✓ InstructEdit [194] Text ✓ ✓ ✓ ✓ ✓ Direct Inversion [195] Text ✓ ✓ ✓ ✓ ✓ DDPM Inversion [196] Text [197] Layout ✓ ✓ LEDITS++ [198] Text [208] Text ✓ ✓ ✓ ✓ TIC [209] Text, Mask ✓ Diffusion Brush [210] Text, Mask ✓ Self-guidance [211] Layout ✓ ✓ P2P [212] Text…”

mentioning

confidence: 99%

See 4 more Smart Citations

M3VSNET: Unsupervised Multi-Metric Multi-View Stereo Network

Huang

et al. 2021

2021 IEEE International Conference on Image Processing (ICIP)

View full text Add to dashboard Cite

The present Multi-view stereo (MVS) methods with supervised learning-based networks have an impressive performance comparing with traditional MVS methods. However, the ground-truth depth maps for training are hard to be obtained and are within limited kinds of scenarios. In this paper, we propose a novel unsupervised multi-metric MVS network, named M 3 VSNet, for dense point cloud reconstruction without any supervision. To improve the robustness and completeness of point cloud reconstruction, we propose a novel multi-metric loss function that combines pixel-wise and feature-wise loss function to learn the inherent constraints from different perspectives of matching correspondences. Besides, we also incorporate the normal-depth consistency in the 3D point cloud format to improve the accuracy and continuity of the estimated depth maps. Experimental results show that M 3 VSNet establishes the state-of-the-arts unsupervised method and achieves better performance than previous supervised MVSNet on the DTU dataset and demonstrates the powerful generalization ability on the Tanks & Temples benchmark with effective improvement.

show abstract