SUBHANKAR MISHRA
ଶୁଭଙ୍କର ମିଶ୍ର
Faculty, School of Computer Sciences, NISER
ଅଧ୍ୟାପକ, ସଂଗଣକ ବିଜ୍ଞାନ ବିଦ୍ୟାଳୟ, ନାଇଜର
Computer Vision - IIIT Bhubaneswar 2024-25 Odd Semester
Syllabus
- Imaging (Formation, Sensing, Processing)
- Edge Detection, Boundary Detection, SIFT Detector, Image Stitching, Face Detection
- Image Processing (Classification, Segmentation, Detection)
Grading scheme
Grading will be absolute.
- Assessment - 20 marks
- Midterm - 30 marks
- Endterm - 50 marks
- Total -100 marks
Assignment
Title of the talk
Name, Roll
Action Detection via an Image Diffusion Process
Aabhas Agarwal, B421002
AVID: ANY LENGTH VIDEO INPAINTING WITH DIFFUSION MODEL
Swayamshree Nanda, B421062
Object Detection with Self-Supervised Scene Adaptation
Prakruti Priyadarshini, B421032
~
Improving Table Structure Recognition With Visual-Alignment
Sequential
Coordinate Modeling
Shreeya Mishra, B421046
Faces that Speak:Jointly Synthesizing Talking Face and Speech from Text
Anuradha Lenka, B421008
Customizing Realistic Human Photos via Stacked ID
Embedding
Suman Sahoo, B421056
Color Shift Estimation-and-Correction for Image
Enhancement
Sumit Bhusan Panda, B421057
RealCustom: Narrowing Real Text Word for Real-Time Open-Domain
Text-to-Image Customization
Amisha Nayak, B421004
Improving Commonsense in Vision-Language Models via Knowledge
Graph Riddles
Sushobhan Tripathy, B421058
LIMAP
Simran Patro, B421043
DETRs With Collaborative Hybrid Assignments
Training
Ravi kumar, B421039
Active Prompt Learning in Vision Language Models
Pratik Prakhar, B421033
3D Agent-Based Visual Trajectory Prediction
Swastik Pradhan, B421061
Vid2Seq: Large-Scale Pretraining of a Visual Language Model for Dense Video Captioning
Harshit Goyal, B421024
HAVE-FUN: Human Avatar Reconstruction from
Few-Shot Unconstrained Images
Pulkit Sinha, B321059
InstructPix2Pix: Learning to Follow Image Editing Instructions
Mohammad Talha Quamar, B421027
Describing Differences in Image Sets with Natural Language
Yash Raj Singh, B421066
PREIM3D: 3D Consistent Precise Image Attribute Editing from a
Single Image
Hemant Sah, B421025
CG
Unsupervised Contour Tracking of Live Cells by Mechanical and Cycle Consistency
Losses
Rimi karan, B421040
CG
HOI: Contact Guided 3D Human Object Interaction Generation
Hrishikesh
Chandra, B421026
CXTrack : Improving 3D Point Cloud Tracking
with Contextual Information
Shrey Sahay, B421047
Blind Spot Denoising
Subrat Kumar Swain, B421055
Multiview Human Action Recognition
Naincy
Chourasia, B421028
Neural Implicit Morphing of Face Image
Naincy
Chourasia, B421028
Text-guided 3D Motion Generation for
Hand-Object Interaction
Shubhank Nagar, B421048
Automatic Controllable Colorization via
Imagination
B Prasant Patnaik, B421014
Feedback-Guided Autonomous Driving
Prerna
Sahu, B4210136
Drag Your GAN: Interactive Point-based
Manipulation on the Generative Image Manifold
Bighnaraj Mohapatra, B421019
Hybrid Functional Maps for Crease-Aware
Non-Isometric Shape Matching
Pratyush Pandey, B421035
High-Resolution Text-to-3D Content Creation
Baivab Kundu, B421017
Blur2Blur: Blur Conversion for Unsupervised Image Deblurring
on Unknown Domains
Ayush Raj, B421013
Im2Hands
Swagnik Saha, B421060
AutoAD: Movie Description in Context
Amit
Kumar Mohapatra, B421005
Class-Consistent and Diverse Image Generation Through StyleGAN
Ashutosh Panda, B421012
3D Paintbrush: Local Stylization of 3D Shapes
with Cascaded Score Distillation
Akanshu Aich, B221008
DressCode: Autoregressively Sewing and Generating Garments
from Text
Guidance
Baibhav Kumar, B421016
3D Highlighter
Tannushree Rana, B421063
A Semi-supervised Nighttime Dehazing Baseline
with Spatial-Frequency Aware
and Realistic Brightness Constraint
Balkrishna Bharti, B421018
Vlogger: Make Your Dream A Vlog,A generic AI
system for generating a minute-level video blog.
Paramjit Singh, B421030
Edit One for All: Interactive Batch Image Editing.pdf
A
Shantanu, B421001
Referring Expression Counting
Tusar Kumar
Nayak, B421065
StyleGAN for Class-Consistent and Diverse
Image Synthesis
Ritish Raj Ratan, B421042
Filter-Guided Diffusion for Controllable Image
Generation
Saswat Jagannath Mishra, B421044
Simultaneous SuperResolution And Deblurring Of Text Images
Pratik Ranjan Sau, B421034
SpatialTracker: Tracking Any 2D Pixels in 3D Space
Ankit Saha, B421007
SVGDreamer: Text Guided SVG Generation with Diffusion Model
Ehtesham Alam, B421021
Diffusion Model Alignment Using Direct Preference Optimization
Ardhi Dattatreya Varma, B421009
Single-Image Crowd Counting via Multi-Column
CNN
Abhay Rajpoot,B421003
Physical Property Understanding from Language-Embedded Feature
Fields
Ashis Choudhury, B421010
Open-set Bias Detection in Text-to-Image Generative
Models
Siddhant Srivastav, B421050
Iterative Vision-and-Language Navigation
Sidharth Choudhury, B221052
Neural Exposure Fusion for High-Dynamic Range Object Detection
Harshit Goel, B421023
Intrinsic Image Diffusion for Indoor Single-view Material
Estimation
Raushan Kumar, B421038
RegionGPT: Towards Region Understanding Vision Language Model
Ashish Upadhyay, B421011
Diffusion Illusions: Hiding Images in Plain Sight
Sthiti Pragyan Panda, B421053
Neural Implicit Morphing of Face Image
Naincy Chourasia,
B421028
Submission guidelines:
- Clone GitHub
- index.html
- If this is the first time, create a new entry (a template is given), project title,
name, roll.
- You will add/update the links associated with your submission.
- Projects/Presentation folder
- If this is the first time, create a new folder under presentation folder.
- Add/update your files in that folder only. Do not make any changes other than your
own.
- Create a pull request after the changes are done
Books
Some recommended books on Computer Vision.
- Szeliski, Richard. Computer vision: algorithms and applications. Springer Nature, 2022.
- Forsyth, David A., and Jean Ponce. Computer vision: a modern approach. prentice hall
professional
technical reference, 2002.
Academic Integrity
Any plagiarism, copying, allowing copying, unpermitted aid will lead to 'zero' in the
assignment/exam/project.