Tribhuvan University, Institute of Engineering, Thapathali Campus
UGC Nepal accreditation badge
Accredited by UGC NepalUniversity Grants CommissionQuality Education Since 1967 A.D.

TCIOE E-Library

The institutional repository of Thapathali Campus, Institute of Engineering, Tribhuvan University.

  • Theses, project reports and research papers from all departments
  • Journals, conference proceedings and faculty publications
  • Course materials, question banks and reference collections

Browse the communities below or use the search to find what you are looking for.

Browse by type

Campus-wide collections gathered from every department.

Departments

Jump straight to a department collection.

View full tree

Recent Submissions

  • Item type:Item,
    Wavelet-space representations for neural super-resolution in rendering pipelines
    (Elsevier, 2026)
    Poudel, Prateek
    ;
    Aryal, Prashant
    ;
    Kunwar, Kirtan
    ;
    Nepal, Navin
    ;
    Baniya Kshatri, Dinesh
    We investigate the use of wavelet-space feature decomposition in neural super-resolution for rendering pipelines. Building on recent neural upscaling frameworks, we introduce a formulation that predicts stationary wavelet coefficients rather than directly regressing RGB values. This frequency-aware decomposition separates low- and high-frequency components, enabling sharper texture recovery and reducing blur in challenging regions. Unlike conventional wavelet transforms, our use of the stationary wavelet transform (SWT) preserves spatial alignment across subbands, allowing the network to integrate G-buffer attributes and temporally warped history frames in a shift-invariant manner. The predicted coefficients are recombined through inverse wavelet synthesis, producing resolution-consistent reconstructions across arbitrary scale factors. We conduct extensive evaluations and ablations, showing that incorporating SWT yields superior perceptual quality compared to industry baselines, while maintaining real-time performance on modern hardware. Taken together, our results suggest that wavelet-domain neural super-resolution provides a principled and efficient path toward higher-quality real-time rendering, with broader implications for neural rendering and graphics applications.
  • Item type:Item,
    Annual Report 2081/2082
    (Thapathali Campus, Institute of Engineering, 2026-03-13)
    Thapathali Campus, Institute of Engineering
  • Item type:Item,
    Industrial Vision (Vol.1) 2014
    (Department of Industrial Engineering, Thapathali Campus, 2014-02-15)
    Society of Industrial Engineering Students (SOIES)
  • Item type:Item,
    Industrial Vision (Vol.3) 2016
    (Department of Industrial Engineering, Thapathali Campus, 2016-02-15)
    Society of Industrial Engineering Students (SOIES)
  • Item type:Item,
    Industrial Vision (Vol.2) 2015
    (Department of Industrial Engineering, Thapathali Campus, 2015-02-15)
    Society of Industrial Engineering Students (SOIES)